* [RFC PATCH 02/17] security: Add hooks to rule on setting a watch [ver #4]
From: David Howells @ 2020-03-09 12:17 UTC (permalink / raw)
To: torvalds, viro
Cc: Casey Schaufler, Stephen Smalley, linux-security-module, dhowells,
dhowells, casey, sds, nicolas.dichtel, raven, christian, andres,
jlayton, dray, kzak, keyrings, linux-api, linux-fsdevel,
linux-security-module, linux-kernel
In-Reply-To: <158375623086.334846.16121725232323108842.stgit@warthog.procyon.org.uk>
Add security hooks that will allow an LSM to rule on whether or not a watch
may be set. More than one hook is required as the watches watch different
types of object.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Casey Schaufler <casey@schaufler-ca.com>
cc: Stephen Smalley <sds@tycho.nsa.gov>
cc: linux-security-module@vger.kernel.org
---
include/linux/lsm_hooks.h | 24 ++++++++++++++++++++++++
include/linux/security.h | 17 +++++++++++++++++
security/security.c | 14 ++++++++++++++
3 files changed, 55 insertions(+)
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 20d8cf194fb7..79d7c73676d7 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1416,6 +1416,18 @@
* @ctx is a pointer in which to place the allocated security context.
* @ctxlen points to the place to put the length of @ctx.
*
+ * Security hooks for the general notification queue:
+ *
+ * @watch_key:
+ * Check to see if a process is allowed to watch for event notifications
+ * from a key or keyring.
+ * @key: The key to watch.
+ *
+ * @watch_devices:
+ * Check to see if a process is allowed to watch for event notifications
+ * from devices (as a global set).
+ *
+ *
* Security hooks for using the eBPF maps and programs functionalities through
* eBPF syscalls.
*
@@ -1698,6 +1710,12 @@ union security_list_options {
int (*inode_notifysecctx)(struct inode *inode, void *ctx, u32 ctxlen);
int (*inode_setsecctx)(struct dentry *dentry, void *ctx, u32 ctxlen);
int (*inode_getsecctx)(struct inode *inode, void **ctx, u32 *ctxlen);
+#ifdef CONFIG_KEY_NOTIFICATIONS
+ int (*watch_key)(struct key *key);
+#endif
+#ifdef CONFIG_DEVICE_NOTIFICATIONS
+ int (*watch_devices)(void);
+#endif
#ifdef CONFIG_SECURITY_NETWORK
int (*unix_stream_connect)(struct sock *sock, struct sock *other,
@@ -1985,6 +2003,12 @@ struct security_hook_heads {
struct hlist_head inode_notifysecctx;
struct hlist_head inode_setsecctx;
struct hlist_head inode_getsecctx;
+#ifdef CONFIG_KEY_NOTIFICATIONS
+ struct hlist_head watch_key;
+#endif
+#ifdef CONFIG_DEVICE_NOTIFICATIONS
+ struct hlist_head watch_devices;
+#endif
#ifdef CONFIG_SECURITY_NETWORK
struct hlist_head unix_stream_connect;
struct hlist_head unix_may_send;
diff --git a/include/linux/security.h b/include/linux/security.h
index 64b19f050343..7a36064a64ea 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1276,6 +1276,23 @@ static inline int security_locked_down(enum lockdown_reason what)
}
#endif /* CONFIG_SECURITY */
+#if defined(CONFIG_SECURITY) && defined(CONFIG_KEY_NOTIFICATIONS)
+int security_watch_key(struct key *key);
+#else
+static inline int security_watch_key(struct key *key)
+{
+ return 0;
+}
+#endif
+#if defined(CONFIG_SECURITY) && defined(CONFIG_DEVICE_NOTIFICATIONS)
+int security_watch_devices(void);
+#else
+static inline int security_watch_devices(void)
+{
+ return 0;
+}
+#endif
+
#ifdef CONFIG_SECURITY_NETWORK
int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk);
diff --git a/security/security.c b/security/security.c
index 565bc9b67276..22877f47cf62 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1988,6 +1988,20 @@ int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen)
}
EXPORT_SYMBOL(security_inode_getsecctx);
+#ifdef CONFIG_KEY_NOTIFICATIONS
+int security_watch_key(struct key *key)
+{
+ return call_int_hook(watch_key, 0, key);
+}
+#endif
+
+#ifdef CONFIG_DEVICE_NOTIFICATIONS
+int security_watch_devices(void)
+{
+ return call_int_hook(watch_devices, 0);
+}
+#endif
+
#ifdef CONFIG_SECURITY_NETWORK
int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk)
^ permalink raw reply related
* [RFC PATCH 03/17] security: Add a hook for the point of notification insertion [ver #4]
From: David Howells @ 2020-03-09 12:17 UTC (permalink / raw)
To: torvalds, viro
Cc: Casey Schaufler, Stephen Smalley, linux-security-module, dhowells,
dhowells, casey, sds, nicolas.dichtel, raven, christian, andres,
jlayton, dray, kzak, keyrings, linux-api, linux-fsdevel,
linux-security-module, linux-kernel
In-Reply-To: <158375623086.334846.16121725232323108842.stgit@warthog.procyon.org.uk>
Add a security hook that allows an LSM to rule on whether a notification
message is allowed to be inserted into a particular watch queue.
The hook is given the following information:
(1) The credentials of the triggerer (which may be init_cred for a system
notification, eg. a hardware error).
(2) The credentials of the whoever set the watch.
(3) The notification message.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Casey Schaufler <casey@schaufler-ca.com>
cc: Stephen Smalley <sds@tycho.nsa.gov>
cc: linux-security-module@vger.kernel.org
---
include/linux/lsm_hooks.h | 14 ++++++++++++++
include/linux/security.h | 14 ++++++++++++++
security/security.c | 9 +++++++++
3 files changed, 37 insertions(+)
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 79d7c73676d7..16530255dc11 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1427,6 +1427,12 @@
* Check to see if a process is allowed to watch for event notifications
* from devices (as a global set).
*
+ * @post_notification:
+ * Check to see if a watch notification can be posted to a particular
+ * queue.
+ * @w_cred: The credentials of the whoever set the watch.
+ * @cred: The event-triggerer's credentials
+ * @n: The notification being posted
*
* Security hooks for using the eBPF maps and programs functionalities through
* eBPF syscalls.
@@ -1716,6 +1722,11 @@ union security_list_options {
#ifdef CONFIG_DEVICE_NOTIFICATIONS
int (*watch_devices)(void);
#endif
+#ifdef CONFIG_WATCH_QUEUE
+ int (*post_notification)(const struct cred *w_cred,
+ const struct cred *cred,
+ struct watch_notification *n);
+#endif
#ifdef CONFIG_SECURITY_NETWORK
int (*unix_stream_connect)(struct sock *sock, struct sock *other,
@@ -2009,6 +2020,9 @@ struct security_hook_heads {
#ifdef CONFIG_DEVICE_NOTIFICATIONS
struct hlist_head watch_devices;
#endif
+#ifdef CONFIG_WATCH_QUEUE
+ struct hlist_head post_notification;
+#endif /* CONFIG_WATCH_QUEUE */
#ifdef CONFIG_SECURITY_NETWORK
struct hlist_head unix_stream_connect;
struct hlist_head unix_may_send;
diff --git a/include/linux/security.h b/include/linux/security.h
index 7a36064a64ea..910a1efa9a79 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -57,6 +57,8 @@ struct mm_struct;
struct fs_context;
struct fs_parameter;
enum fs_value_type;
+struct watch;
+struct watch_notification;
/* Default (no) options for the capable function */
#define CAP_OPT_NONE 0x0
@@ -1292,6 +1294,18 @@ static inline int security_watch_devices(void)
return 0;
}
#endif
+#if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE)
+int security_post_notification(const struct cred *w_cred,
+ const struct cred *cred,
+ struct watch_notification *n);
+#else
+static inline int security_post_notification(const struct cred *w_cred,
+ const struct cred *cred,
+ struct watch_notification *n)
+{
+ return 0;
+}
+#endif
#ifdef CONFIG_SECURITY_NETWORK
diff --git a/security/security.c b/security/security.c
index 22877f47cf62..db7b574c9c70 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1988,6 +1988,15 @@ int security_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen)
}
EXPORT_SYMBOL(security_inode_getsecctx);
+#ifdef CONFIG_WATCH_QUEUE
+int security_post_notification(const struct cred *w_cred,
+ const struct cred *cred,
+ struct watch_notification *n)
+{
+ return call_int_hook(post_notification, 0, w_cred, cred, n);
+}
+#endif /* CONFIG_WATCH_QUEUE */
+
#ifdef CONFIG_KEY_NOTIFICATIONS
int security_watch_key(struct key *key)
{
^ permalink raw reply related
* [RFC PATCH 04/17] pipe: Add O_NOTIFICATION_PIPE [ver #4]
From: David Howells @ 2020-03-09 12:17 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, dhowells, casey, sds, nicolas.dichtel, raven, christian,
andres, jlayton, dray, kzak, keyrings, linux-api, linux-fsdevel,
linux-security-module, linux-kernel
In-Reply-To: <158375623086.334846.16121725232323108842.stgit@warthog.procyon.org.uk>
Add an O_NOTIFICATION_PIPE flag that can be passed to pipe2() to indicate
that the pipe being created is going to be used for notifications. This
suppresses the use of splice(), vmsplice(), tee() and sendfile() on the
pipe as calling iov_iter_revert() on a pipe when a kernel notification
message has been inserted into the middle of a multi-buffer splice will be
messy.
The flag is given the same value as O_EXCL as it seems unlikely that
this flag will ever be applicable to pipes and I don't want to use up
another O_* bit unnecessarily. An alternative could be to add a pipe3()
system call.
Signed-off-by: David Howells <dhowells@redhat.com>
---
include/uapi/linux/watch_queue.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/include/uapi/linux/watch_queue.h b/include/uapi/linux/watch_queue.h
index 5f3d21e8a34b..9df72227f515 100644
--- a/include/uapi/linux/watch_queue.h
+++ b/include/uapi/linux/watch_queue.h
@@ -3,6 +3,9 @@
#define _UAPI_LINUX_WATCH_QUEUE_H
#include <linux/types.h>
+#include <linux/fcntl.h>
+
+#define O_NOTIFICATION_PIPE O_EXCL /* Parameter to pipe2() selecting notification pipe */
enum watch_notification_type {
WATCH_TYPE_META = 0, /* Special record */
^ permalink raw reply related
* [RFC PATCH 05/17] pipe: Add general notification queue support [ver #4]
From: David Howells @ 2020-03-09 12:17 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, dhowells, casey, sds, nicolas.dichtel, raven, christian,
andres, jlayton, dray, kzak, keyrings, linux-api, linux-fsdevel,
linux-security-module, linux-kernel
In-Reply-To: <158375623086.334846.16121725232323108842.stgit@warthog.procyon.org.uk>
Make it possible to have a general notification queue built on top of a
standard pipe. Notifications are 'spliced' into the pipe and then read
out. splice(), vmsplice() and sendfile() are forbidden on pipes used for
notifications as post_one_notification() cannot take pipe->mutex. This
means that notifications could be posted in between individual pipe
buffers, making iov_iter_revert() difficult to effect.
The way the notification queue is used is:
(1) An application opens a pipe with a special flag and indicates the
number of messages it wishes to be able to queue at once (this can
only be set once):
pipe2(fds, O_NOTIFICATION_PIPE);
ioctl(fds[0], IOC_WATCH_QUEUE_SET_SIZE, queue_depth);
(2) The application then uses poll() and read() as normal to extract data
from the pipe. read() will return multiple notifications if the
buffer is big enough, but it will not split a notification across
buffers - rather it will return a short read or EMSGSIZE.
Notification messages include a length in the header so that the
caller can split them up.
Each message has a header that describes it:
struct watch_notification {
__u32 type:24;
__u32 subtype:8;
__u32 info;
};
The type indicates the source (eg. mount tree changes, superblock events,
keyring changes, block layer events) and the subtype indicates the event
type (eg. mount, unmount; EIO, EDQUOT; link, unlink). The info field
indicates a number of things, including the entry length, an ID assigned to
a watchpoint contributing to this buffer and type-specific flags.
Supplementary data, such as the key ID that generated an event, can be
attached in additional slots. The maximum message size is 127 bytes.
Messages may not be padded or aligned, so there is no guarantee, for
example, that the notification type will be on a 4-byte bounary.
Signed-off-by: David Howells <dhowells@redhat.com>
---
Documentation/userspace-api/ioctl/ioctl-number.rst | 1
Documentation/watch_queue.rst | 354 +++++++++++
fs/pipe.c | 206 ++++--
fs/splice.c | 12
include/linux/pipe_fs_i.h | 19 +
include/linux/watch_queue.h | 127 ++++
include/uapi/linux/watch_queue.h | 20 +
init/Kconfig | 12
kernel/Makefile | 1
kernel/watch_queue.c | 657 ++++++++++++++++++++
10 files changed, 1333 insertions(+), 76 deletions(-)
create mode 100644 Documentation/watch_queue.rst
create mode 100644 include/linux/watch_queue.h
create mode 100644 kernel/watch_queue.c
diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index 2e91370dc159..cdf8551d70d7 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -201,6 +201,7 @@ Code Seq# Include File Comments
'W' 00-1F linux/wanrouter.h conflict! (pre 3.9)
'W' 00-3F sound/asound.h conflict!
'W' 40-5F drivers/pci/switch/switchtec.c
+'W' 60-61 linux/watch_queue.h
'X' all fs/xfs/xfs_fs.h, conflict!
fs/xfs/linux-2.6/xfs_ioctl32.h,
include/linux/falloc.h,
diff --git a/Documentation/watch_queue.rst b/Documentation/watch_queue.rst
new file mode 100644
index 000000000000..d8f70282d247
--- /dev/null
+++ b/Documentation/watch_queue.rst
@@ -0,0 +1,354 @@
+==============================
+General notification mechanism
+==============================
+
+The general notification mechanism is built on top of the standard pipe driver
+whereby it effectively splices notification messages from the kernel into pipes
+opened by userspace. This can be used in conjunction with::
+
+ * Key/keyring notifications
+
+ * General device event notifications
+
+
+The notifications buffers can be enabled by:
+
+ "General setup"/"General notification queue"
+ (CONFIG_WATCH_QUEUE)
+
+This document has the following sections:
+
+.. contents:: :local:
+
+
+Overview
+========
+
+This facility appears as a pipe that is opened in a special mode. The pipe's
+internal ring buffer is used to hold messages that are generated by the kernel.
+These messages are then read out by read(). Splice and similar are disabled on
+such pipes due to them wanting to, under some circumstances, revert their
+additions to the ring - which might end up interleaved with notification
+messages.
+
+The owner of the pipe has to tell the kernel which sources it would like to
+watch through that pipe. Only sources that have been connected to a pipe will
+insert messages into it. Note that a source may be bound to multiple pipes and
+insert messages into all of them simultaneously.
+
+Filters may also be emplaced on a pipe so that certain source types and
+subevents can be ignored if they're not of interest.
+
+A message will be discarded if there isn't a slot available in the ring or if
+no preallocated message buffer is available. In both of these cases, read()
+will insert a WATCH_META_LOSS_NOTIFICATION message into the output buffer after
+the last message currently in the buffer has been read.
+
+Note that when producing a notification, the kernel does not wait for the
+consumers to collect it, but rather just continues on. This means that
+notifications can be generated whilst spinlocks are held and also protects the
+kernel from being held up indefinitely by a userspace malfunction.
+
+
+Message Structure
+=================
+
+Notification messages begin with a short header::
+
+ struct watch_notification {
+ __u32 type:24;
+ __u32 subtype:8;
+ __u32 info;
+ };
+
+"type" indicates the source of the notification record and "subtype" indicates
+the type of record from that source (see the Watch Sources section below). The
+type may also be "WATCH_TYPE_META". This is a special record type generated
+internally by the watch queue itself. There are two subtypes:
+
+ * WATCH_META_REMOVAL_NOTIFICATION
+ * WATCH_META_LOSS_NOTIFICATION
+
+The first indicates that an object on which a watch was installed was removed
+or destroyed and the second indicates that some messages have been lost.
+
+"info" indicates a bunch of things, including:
+
+ * The length of the message in bytes, including the header (mask with
+ WATCH_INFO_LENGTH and shift by WATCH_INFO_LENGTH__SHIFT). This indicates
+ the size of the record, which may be between 8 and 127 bytes.
+
+ * The watch ID (mask with WATCH_INFO_ID and shift by WATCH_INFO_ID__SHIFT).
+ This indicates that caller's ID of the watch, which may be between 0
+ and 255. Multiple watches may share a queue, and this provides a means to
+ distinguish them.
+
+ * A type-specific field (WATCH_INFO_TYPE_INFO). This is set by the
+ notification producer to indicate some meaning specific to the type and
+ subtype.
+
+Everything in info apart from the length can be used for filtering.
+
+The header can be followed by supplementary information. The format of this is
+at the discretion is defined by the type and subtype.
+
+
+Watch List (Notification Source) API
+====================================
+
+A "watch list" is a list of watchers that are subscribed to a source of
+notifications. A list may be attached to an object (say a key or a superblock)
+or may be global (say for device events). From a userspace perspective, a
+non-global watch list is typically referred to by reference to the object it
+belongs to (such as using KEYCTL_NOTIFY and giving it a key serial number to
+watch that specific key).
+
+To manage a watch list, the following functions are provided:
+
+ * ``void init_watch_list(struct watch_list *wlist,
+ void (*release_watch)(struct watch *wlist));``
+
+ Initialise a watch list. If ``release_watch`` is not NULL, then this
+ indicates a function that should be called when the watch_list object is
+ destroyed to discard any references the watch list holds on the watched
+ object.
+
+ * ``void remove_watch_list(struct watch_list *wlist);``
+
+ This removes all of the watches subscribed to a watch_list and frees them
+ and then destroys the watch_list object itself.
+
+
+Watch Queue (Notification Output) API
+=====================================
+
+A "watch queue" is the buffer allocated by an application that notification
+records will be written into. The workings of this are hidden entirely inside
+of the watch_queue device driver, but it is necessary to gain a reference to it
+to set a watch. These can be managed with:
+
+ * ``struct watch_queue *get_watch_queue(int fd);``
+
+ Since watch queues are indicated to the kernel by the fd of the pipe that
+ implements the buffer, userspace must hand that fd through a system call.
+ This can be used to look up an opaque pointer to the watch queue from the
+ system call.
+
+ * ``void put_watch_queue(struct watch_queue *wqueue);``
+
+ This discards the reference obtained from ``get_watch_queue()``.
+
+
+Watch Subscription API
+======================
+
+A "watch" is a subscription on a watch list, indicating the watch queue, and
+thus the buffer, into which notification records should be written. The watch
+queue object may also carry filtering rules for that object, as set by
+userspace. Some parts of the watch struct can be set by the driver::
+
+ struct watch {
+ union {
+ u32 info_id; /* ID to be OR'd in to info field */
+ ...
+ };
+ void *private; /* Private data for the watched object */
+ u64 id; /* Internal identifier */
+ ...
+ };
+
+The ``info_id`` value should be an 8-bit number obtained from userspace and
+shifted by WATCH_INFO_ID__SHIFT. This is OR'd into the WATCH_INFO_ID field of
+struct watch_notification::info when and if the notification is written into
+the associated watch queue buffer.
+
+The ``private`` field is the driver's data associated with the watch_list and
+is cleaned up by the ``watch_list::release_watch()`` method.
+
+The ``id`` field is the source's ID. Notifications that are posted with a
+different ID are ignored.
+
+The following functions are provided to manage watches:
+
+ * ``void init_watch(struct watch *watch, struct watch_queue *wqueue);``
+
+ Initialise a watch object, setting its pointer to the watch queue, using
+ appropriate barriering to avoid lockdep complaints.
+
+ * ``int add_watch_to_object(struct watch *watch, struct watch_list *wlist);``
+
+ Subscribe a watch to a watch list (notification source). The
+ driver-settable fields in the watch struct must have been set before this
+ is called.
+
+ * ``int remove_watch_from_object(struct watch_list *wlist,
+ struct watch_queue *wqueue,
+ u64 id, false);``
+
+ Remove a watch from a watch list, where the watch must match the specified
+ watch queue (``wqueue``) and object identifier (``id``). A notification
+ (``WATCH_META_REMOVAL_NOTIFICATION``) is sent to the watch queue to
+ indicate that the watch got removed.
+
+ * ``int remove_watch_from_object(struct watch_list *wlist, NULL, 0, true);``
+
+ Remove all the watches from a watch list. It is expected that this will be
+ called preparatory to destruction and that the watch list will be
+ inaccessible to new watches by this point. A notification
+ (``WATCH_META_REMOVAL_NOTIFICATION``) is sent to the watch queue of each
+ subscribed watch to indicate that the watch got removed.
+
+
+Notification Posting API
+========================
+
+To post a notification to watch list so that the subscribed watches can see it,
+the following function should be used::
+
+ void post_watch_notification(struct watch_list *wlist,
+ struct watch_notification *n,
+ const struct cred *cred,
+ u64 id);
+
+The notification should be preformatted and a pointer to the header (``n``)
+should be passed in. The notification may be larger than this and the size in
+units of buffer slots is noted in ``n->info & WATCH_INFO_LENGTH``.
+
+The ``cred`` struct indicates the credentials of the source (subject) and is
+passed to the LSMs, such as SELinux, to allow or suppress the recording of the
+note in each individual queue according to the credentials of that queue
+(object).
+
+The ``id`` is the ID of the source object (such as the serial number on a key).
+Only watches that have the same ID set in them will see this notification.
+
+
+Watch Sources
+=============
+
+Any particular buffer can be fed from multiple sources. Sources include:
+
+ * WATCH_TYPE_KEY_NOTIFY
+
+ Notifications of this type indicate changes to keys and keyrings, including
+ the changes of keyring contents or the attributes of keys.
+
+ See Documentation/security/keys/core.rst for more information.
+
+ * WATCH_TYPE_BLOCK_NOTIFY
+
+ Notifications of this type indicate block layer events, such as I/O errors
+ or temporary link loss. Watches of this type are set on a global queue.
+
+
+Event Filtering
+===============
+
+Once a watch queue has been created, a set of filters can be applied to limit
+the events that are received using::
+
+ struct watch_notification_filter filter = {
+ ...
+ };
+ ioctl(fd, IOC_WATCH_QUEUE_SET_FILTER, &filter)
+
+The filter description is a variable of type::
+
+ struct watch_notification_filter {
+ __u32 nr_filters;
+ __u32 __reserved;
+ struct watch_notification_type_filter filters[];
+ };
+
+Where "nr_filters" is the number of filters in filters[] and "__reserved"
+should be 0. The "filters" array has elements of the following type::
+
+ struct watch_notification_type_filter {
+ __u32 type;
+ __u32 info_filter;
+ __u32 info_mask;
+ __u32 subtype_filter[8];
+ };
+
+Where:
+
+ * ``type`` is the event type to filter for and should be something like
+ "WATCH_TYPE_KEY_NOTIFY"
+
+ * ``info_filter`` and ``info_mask`` act as a filter on the info field of the
+ notification record. The notification is only written into the buffer if::
+
+ (watch.info & info_mask) == info_filter
+
+ This could be used, for example, to ignore events that are not exactly on
+ the watched point in a mount tree.
+
+ * ``subtype_filter`` is a bitmask indicating the subtypes that are of
+ interest. Bit 0 of subtype_filter[0] corresponds to subtype 0, bit 1 to
+ subtype 1, and so on.
+
+If the argument to the ioctl() is NULL, then the filters will be removed and
+all events from the watched sources will come through.
+
+
+Userspace Code Example
+======================
+
+A buffer is created with something like the following::
+
+ pipe2(fds, O_TMPFILE);
+ ioctl(fds[1], IOC_WATCH_QUEUE_SET_SIZE, 256);
+
+It can then be set to receive keyring change notifications and device event
+notifications::
+
+ keyctl(KEYCTL_WATCH_KEY, KEY_SPEC_SESSION_KEYRING, fds[1], 0x01);
+ watch_devices(fds[1], 0x2);
+
+The notifications can then be consumed by something like the following::
+
+ static void consumer(int rfd, struct watch_queue_buffer *buf)
+ {
+ unsigned char buffer[128];
+ ssize_t buf_len;
+
+ while (buf_len = read(rfd, buffer, sizeof(buffer)),
+ buf_len > 0
+ ) {
+ void *p = buffer;
+ void *end = buffer + buf_len;
+ while (p < end) {
+ union {
+ struct watch_notification n;
+ unsigned char buf1[128];
+ } n;
+ size_t largest, len;
+
+ largest = end - p;
+ if (largest > 128)
+ largest = 128;
+ memcpy(&n, p, largest);
+
+ len = (n->info & WATCH_INFO_LENGTH) >>
+ WATCH_INFO_LENGTH__SHIFT;
+ if (len == 0 || len > largest)
+ return;
+
+ switch (n.n.type) {
+ case WATCH_TYPE_META:
+ got_meta(&n.n);
+ case WATCH_TYPE_KEY_NOTIFY:
+ saw_key_change(&n.n);
+ break;
+ case WATCH_TYPE_BLOCK_NOTIFY:
+ saw_block_event(&n.n);
+ break;
+ case WATCH_TYPE_USB_NOTIFY:
+ saw_usb_event(&n.n);
+ break;
+ }
+
+ p += len;
+ }
+ }
+ }
diff --git a/fs/pipe.c b/fs/pipe.c
index 5a34d6c22d4c..36eedf8cb143 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -24,6 +24,7 @@
#include <linux/syscalls.h>
#include <linux/fcntl.h>
#include <linux/memcontrol.h>
+#include <linux/watch_queue.h>
#include <linux/uaccess.h>
#include <asm/ioctls.h>
@@ -459,6 +460,13 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
goto out;
}
+#ifdef CONFIG_WATCH_QUEUE
+ if (pipe->watch_queue) {
+ ret = -EXDEV;
+ goto out;
+ }
+#endif
+
/*
* Only wake up if the pipe started out empty, since
* otherwise there should be no readers waiting.
@@ -628,22 +636,37 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
int count, head, tail, mask;
switch (cmd) {
- case FIONREAD:
- __pipe_lock(pipe);
- count = 0;
- head = pipe->head;
- tail = pipe->tail;
- mask = pipe->ring_size - 1;
+ case FIONREAD:
+ __pipe_lock(pipe);
+ count = 0;
+ head = pipe->head;
+ tail = pipe->tail;
+ mask = pipe->ring_size - 1;
- while (tail != head) {
- count += pipe->bufs[tail & mask].len;
- tail++;
- }
- __pipe_unlock(pipe);
+ while (tail != head) {
+ count += pipe->bufs[tail & mask].len;
+ tail++;
+ }
+ __pipe_unlock(pipe);
- return put_user(count, (int __user *)arg);
- default:
- return -ENOIOCTLCMD;
+ return put_user(count, (int __user *)arg);
+
+#ifdef CONFIG_WATCH_QUEUE
+ case IOC_WATCH_QUEUE_SET_SIZE: {
+ int ret;
+ __pipe_lock(pipe);
+ ret = watch_queue_set_size(pipe, arg);
+ __pipe_unlock(pipe);
+ return ret;
+ }
+
+ case IOC_WATCH_QUEUE_SET_FILTER:
+ return watch_queue_set_filter(
+ pipe, (struct watch_notification_filter __user *)arg);
+#endif
+
+ default:
+ return -ENOIOCTLCMD;
}
}
@@ -753,27 +776,27 @@ pipe_fasync(int fd, struct file *filp, int on)
return retval;
}
-static unsigned long account_pipe_buffers(struct user_struct *user,
- unsigned long old, unsigned long new)
+unsigned long account_pipe_buffers(struct user_struct *user,
+ unsigned long old, unsigned long new)
{
return atomic_long_add_return(new - old, &user->pipe_bufs);
}
-static bool too_many_pipe_buffers_soft(unsigned long user_bufs)
+bool too_many_pipe_buffers_soft(unsigned long user_bufs)
{
unsigned long soft_limit = READ_ONCE(pipe_user_pages_soft);
return soft_limit && user_bufs > soft_limit;
}
-static bool too_many_pipe_buffers_hard(unsigned long user_bufs)
+bool too_many_pipe_buffers_hard(unsigned long user_bufs)
{
unsigned long hard_limit = READ_ONCE(pipe_user_pages_hard);
return hard_limit && user_bufs > hard_limit;
}
-static bool is_unprivileged_user(void)
+bool pipe_is_unprivileged_user(void)
{
return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
}
@@ -795,12 +818,12 @@ struct pipe_inode_info *alloc_pipe_info(void)
user_bufs = account_pipe_buffers(user, 0, pipe_bufs);
- if (too_many_pipe_buffers_soft(user_bufs) && is_unprivileged_user()) {
+ if (too_many_pipe_buffers_soft(user_bufs) && pipe_is_unprivileged_user()) {
user_bufs = account_pipe_buffers(user, pipe_bufs, 1);
pipe_bufs = 1;
}
- if (too_many_pipe_buffers_hard(user_bufs) && is_unprivileged_user())
+ if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user())
goto out_revert_acct;
pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer),
@@ -812,6 +835,7 @@ struct pipe_inode_info *alloc_pipe_info(void)
pipe->r_counter = pipe->w_counter = 1;
pipe->max_usage = pipe_bufs;
pipe->ring_size = pipe_bufs;
+ pipe->nr_accounted = pipe_bufs;
pipe->user = user;
mutex_init(&pipe->mutex);
return pipe;
@@ -829,7 +853,14 @@ void free_pipe_info(struct pipe_inode_info *pipe)
{
int i;
- (void) account_pipe_buffers(pipe->user, pipe->ring_size, 0);
+#ifdef CONFIG_WATCH_QUEUE
+ if (pipe->watch_queue) {
+ watch_queue_clear(pipe->watch_queue);
+ put_watch_queue(pipe->watch_queue);
+ }
+#endif
+
+ (void) account_pipe_buffers(pipe->user, pipe->nr_accounted, 0);
free_uid(pipe->user);
for (i = 0; i < pipe->ring_size; i++) {
struct pipe_buffer *buf = pipe->bufs + i;
@@ -905,6 +936,17 @@ int create_pipe_files(struct file **res, int flags)
if (!inode)
return -ENFILE;
+ if (flags & O_NOTIFICATION_PIPE) {
+#ifdef CONFIG_WATCH_QUEUE
+ if (watch_queue_init(inode->i_pipe) < 0) {
+ iput(inode);
+ return -ENOMEM;
+ }
+#else
+ return -ENOPKG;
+#endif
+ }
+
f = alloc_file_pseudo(inode, pipe_mnt, "",
O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)),
&pipefifo_fops);
@@ -935,7 +977,7 @@ static int __do_pipe_flags(int *fd, struct file **files, int flags)
int error;
int fdw, fdr;
- if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT))
+ if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT | O_NOTIFICATION_PIPE))
return -EINVAL;
error = create_pipe_files(files, flags);
@@ -1183,42 +1225,12 @@ unsigned int round_pipe_size(unsigned long size)
}
/*
- * Allocate a new array of pipe buffers and copy the info over. Returns the
- * pipe size if successful, or return -ERROR on error.
+ * Resize the pipe ring to a number of slots.
*/
-static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
+int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots)
{
struct pipe_buffer *bufs;
- unsigned int size, nr_slots, head, tail, mask, n;
- unsigned long user_bufs;
- long ret = 0;
-
- size = round_pipe_size(arg);
- nr_slots = size >> PAGE_SHIFT;
-
- if (!nr_slots)
- return -EINVAL;
-
- /*
- * If trying to increase the pipe capacity, check that an
- * unprivileged user is not trying to exceed various limits
- * (soft limit check here, hard limit check just below).
- * Decreasing the pipe capacity is always permitted, even
- * if the user is currently over a limit.
- */
- if (nr_slots > pipe->ring_size &&
- size > pipe_max_size && !capable(CAP_SYS_RESOURCE))
- return -EPERM;
-
- user_bufs = account_pipe_buffers(pipe->user, pipe->ring_size, nr_slots);
-
- if (nr_slots > pipe->ring_size &&
- (too_many_pipe_buffers_hard(user_bufs) ||
- too_many_pipe_buffers_soft(user_bufs)) &&
- is_unprivileged_user()) {
- ret = -EPERM;
- goto out_revert_acct;
- }
+ unsigned int head, tail, mask, n;
/*
* We can shrink the pipe, if arg is greater than the ring occupancy.
@@ -1230,17 +1242,13 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
head = pipe->head;
tail = pipe->tail;
n = pipe_occupancy(pipe->head, pipe->tail);
- if (nr_slots < n) {
- ret = -EBUSY;
- goto out_revert_acct;
- }
+ if (nr_slots < n)
+ return -EBUSY;
bufs = kcalloc(nr_slots, sizeof(*bufs),
GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
- if (unlikely(!bufs)) {
- ret = -ENOMEM;
- goto out_revert_acct;
- }
+ if (unlikely(!bufs))
+ return -ENOMEM;
/*
* The pipe array wraps around, so just start the new one at zero
@@ -1268,15 +1276,67 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
kfree(pipe->bufs);
pipe->bufs = bufs;
pipe->ring_size = nr_slots;
- pipe->max_usage = nr_slots;
+ if (pipe->max_usage > nr_slots)
+ pipe->max_usage = nr_slots;
pipe->tail = tail;
pipe->head = head;
wake_up_interruptible_all(&pipe->rd_wait);
wake_up_interruptible_all(&pipe->wr_wait);
+ return 0;
+}
+
+/*
+ * Allocate a new array of pipe buffers and copy the info over. Returns the
+ * pipe size if successful, or return -ERROR on error.
+ */
+static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
+{
+ unsigned long user_bufs;
+ unsigned int nr_slots, size;
+ long ret = 0;
+
+#ifdef CONFIG_WATCH_QUEUE
+ if (pipe->watch_queue)
+ return -EBUSY;
+#endif
+
+ size = round_pipe_size(arg);
+ nr_slots = size >> PAGE_SHIFT;
+
+ if (!nr_slots)
+ return -EINVAL;
+
+ /*
+ * If trying to increase the pipe capacity, check that an
+ * unprivileged user is not trying to exceed various limits
+ * (soft limit check here, hard limit check just below).
+ * Decreasing the pipe capacity is always permitted, even
+ * if the user is currently over a limit.
+ */
+ if (nr_slots > pipe->max_usage &&
+ size > pipe_max_size && !capable(CAP_SYS_RESOURCE))
+ return -EPERM;
+
+ user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_slots);
+
+ if (nr_slots > pipe->max_usage &&
+ (too_many_pipe_buffers_hard(user_bufs) ||
+ too_many_pipe_buffers_soft(user_bufs)) &&
+ pipe_is_unprivileged_user()) {
+ ret = -EPERM;
+ goto out_revert_acct;
+ }
+
+ ret = pipe_resize_ring(pipe, nr_slots);
+ if (ret < 0)
+ goto out_revert_acct;
+
+ pipe->max_usage = nr_slots;
+ pipe->nr_accounted = nr_slots;
return pipe->max_usage * PAGE_SIZE;
out_revert_acct:
- (void) account_pipe_buffers(pipe->user, nr_slots, pipe->ring_size);
+ (void) account_pipe_buffers(pipe->user, nr_slots, pipe->nr_accounted);
return ret;
}
@@ -1285,9 +1345,17 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg)
* location, so checking ->i_pipe is not enough to verify that this is a
* pipe.
*/
-struct pipe_inode_info *get_pipe_info(struct file *file)
+struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice)
{
- return file->f_op == &pipefifo_fops ? file->private_data : NULL;
+ struct pipe_inode_info *pipe = file->private_data;
+
+ if (file->f_op != &pipefifo_fops || !pipe)
+ return NULL;
+#ifdef CONFIG_WATCH_QUEUE
+ if (for_splice && pipe->watch_queue)
+ return NULL;
+#endif
+ return pipe;
}
long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
@@ -1295,7 +1363,7 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
struct pipe_inode_info *pipe;
long ret;
- pipe = get_pipe_info(file);
+ pipe = get_pipe_info(file, false);
if (!pipe)
return -EBADF;
diff --git a/fs/splice.c b/fs/splice.c
index d671936d0aad..6e6ea30c72b4 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1118,8 +1118,8 @@ static long do_splice(struct file *in, loff_t __user *off_in,
loff_t offset;
long ret;
- ipipe = get_pipe_info(in);
- opipe = get_pipe_info(out);
+ ipipe = get_pipe_info(in, true);
+ opipe = get_pipe_info(out, true);
if (ipipe && opipe) {
if (off_in || off_out)
@@ -1278,7 +1278,7 @@ static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
static long vmsplice_to_user(struct file *file, struct iov_iter *iter,
unsigned int flags)
{
- struct pipe_inode_info *pipe = get_pipe_info(file);
+ struct pipe_inode_info *pipe = get_pipe_info(file, true);
struct splice_desc sd = {
.total_len = iov_iter_count(iter),
.flags = flags,
@@ -1313,7 +1313,7 @@ static long vmsplice_to_pipe(struct file *file, struct iov_iter *iter,
if (flags & SPLICE_F_GIFT)
buf_flag = PIPE_BUF_FLAG_GIFT;
- pipe = get_pipe_info(file);
+ pipe = get_pipe_info(file, true);
if (!pipe)
return -EBADF;
@@ -1766,8 +1766,8 @@ static int link_pipe(struct pipe_inode_info *ipipe,
static long do_tee(struct file *in, struct file *out, size_t len,
unsigned int flags)
{
- struct pipe_inode_info *ipipe = get_pipe_info(in);
- struct pipe_inode_info *opipe = get_pipe_info(out);
+ struct pipe_inode_info *ipipe = get_pipe_info(in, true);
+ struct pipe_inode_info *opipe = get_pipe_info(out, true);
int ret = -EINVAL;
/*
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index d5765039652a..8cd14d72dfd1 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -34,6 +34,7 @@ struct pipe_buffer {
* @tail: The point of buffer consumption
* @max_usage: The maximum number of slots that may be used in the ring
* @ring_size: total number of buffers (should be a power of 2)
+ * @nr_accounted: The amount this pipe accounts for in user->pipe_bufs
* @tmp_page: cached released page
* @readers: number of current readers of this pipe
* @writers: number of current writers of this pipe
@@ -44,6 +45,7 @@ struct pipe_buffer {
* @fasync_writers: writer side fasync
* @bufs: the circular array of pipe buffers
* @user: the user who created this pipe
+ * @watch_queue: If this pipe is a watch_queue, this is the stuff for that
**/
struct pipe_inode_info {
struct mutex mutex;
@@ -52,6 +54,7 @@ struct pipe_inode_info {
unsigned int tail;
unsigned int max_usage;
unsigned int ring_size;
+ unsigned int nr_accounted;
unsigned int readers;
unsigned int writers;
unsigned int files;
@@ -62,6 +65,9 @@ struct pipe_inode_info {
struct fasync_struct *fasync_writers;
struct pipe_buffer *bufs;
struct user_struct *user;
+#ifdef CONFIG_WATCH_QUEUE
+ struct watch_queue *watch_queue;
+#endif
};
/*
@@ -236,9 +242,20 @@ void pipe_buf_mark_unmergeable(struct pipe_buffer *buf);
extern const struct pipe_buf_operations nosteal_pipe_buf_ops;
+#ifdef CONFIG_WATCH_QUEUE
+unsigned long account_pipe_buffers(struct user_struct *user,
+ unsigned long old, unsigned long new);
+bool too_many_pipe_buffers_soft(unsigned long user_bufs);
+bool too_many_pipe_buffers_hard(unsigned long user_bufs);
+bool pipe_is_unprivileged_user(void);
+#endif
+
/* for F_SETPIPE_SZ and F_GETPIPE_SZ */
+#ifdef CONFIG_WATCH_QUEUE
+int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots);
+#endif
long pipe_fcntl(struct file *, unsigned int, unsigned long arg);
-struct pipe_inode_info *get_pipe_info(struct file *file);
+struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice);
int create_pipe_files(struct file **, int);
unsigned int round_pipe_size(unsigned long size);
diff --git a/include/linux/watch_queue.h b/include/linux/watch_queue.h
new file mode 100644
index 000000000000..5e08db2adc31
--- /dev/null
+++ b/include/linux/watch_queue.h
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0
+/* User-mappable watch queue
+ *
+ * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * See Documentation/watch_queue.rst
+ */
+
+#ifndef _LINUX_WATCH_QUEUE_H
+#define _LINUX_WATCH_QUEUE_H
+
+#include <uapi/linux/watch_queue.h>
+#include <linux/kref.h>
+#include <linux/rcupdate.h>
+
+#ifdef CONFIG_WATCH_QUEUE
+
+struct cred;
+
+struct watch_type_filter {
+ enum watch_notification_type type;
+ __u32 subtype_filter[1]; /* Bitmask of subtypes to filter on */
+ __u32 info_filter; /* Filter on watch_notification::info */
+ __u32 info_mask; /* Mask of relevant bits in info_filter */
+};
+
+struct watch_filter {
+ union {
+ struct rcu_head rcu;
+ unsigned long type_filter[2]; /* Bitmask of accepted types */
+ };
+ u32 nr_filters; /* Number of filters */
+ struct watch_type_filter filters[];
+};
+
+struct watch_queue {
+ struct rcu_head rcu;
+ struct watch_filter __rcu *filter;
+ struct pipe_inode_info *pipe; /* The pipe we're using as a buffer */
+ struct hlist_head watches; /* Contributory watches */
+ struct page **notes; /* Preallocated notifications */
+ unsigned long *notes_bitmap; /* Allocation bitmap for notes */
+ struct kref usage; /* Object usage count */
+ spinlock_t lock;
+ unsigned int nr_notes; /* Number of notes */
+ unsigned int nr_pages; /* Number of pages in notes[] */
+ bool defunct; /* T when queues closed */
+};
+
+/*
+ * Representation of a watch on an object.
+ */
+struct watch {
+ union {
+ struct rcu_head rcu;
+ u32 info_id; /* ID to be OR'd in to info field */
+ };
+ struct watch_queue __rcu *queue; /* Queue to post events to */
+ struct hlist_node queue_node; /* Link in queue->watches */
+ struct watch_list __rcu *watch_list;
+ struct hlist_node list_node; /* Link in watch_list->watchers */
+ const struct cred *cred; /* Creds of the owner of the watch */
+ void *private; /* Private data for the watched object */
+ u64 id; /* Internal identifier */
+ struct kref usage; /* Object usage count */
+};
+
+/*
+ * List of watches on an object.
+ */
+struct watch_list {
+ struct rcu_head rcu;
+ struct hlist_head watchers;
+ void (*release_watch)(struct watch *);
+ spinlock_t lock;
+};
+
+extern void __post_watch_notification(struct watch_list *,
+ struct watch_notification *,
+ const struct cred *,
+ u64);
+extern struct watch_queue *get_watch_queue(int);
+extern void put_watch_queue(struct watch_queue *);
+extern void init_watch(struct watch *, struct watch_queue *);
+extern int add_watch_to_object(struct watch *, struct watch_list *);
+extern int remove_watch_from_object(struct watch_list *, struct watch_queue *, u64, bool);
+extern long watch_queue_set_size(struct pipe_inode_info *, unsigned int);
+extern long watch_queue_set_filter(struct pipe_inode_info *,
+ struct watch_notification_filter __user *);
+extern int watch_queue_init(struct pipe_inode_info *);
+extern void watch_queue_clear(struct watch_queue *);
+
+static inline void init_watch_list(struct watch_list *wlist,
+ void (*release_watch)(struct watch *))
+{
+ INIT_HLIST_HEAD(&wlist->watchers);
+ spin_lock_init(&wlist->lock);
+ wlist->release_watch = release_watch;
+}
+
+static inline void post_watch_notification(struct watch_list *wlist,
+ struct watch_notification *n,
+ const struct cred *cred,
+ u64 id)
+{
+ if (unlikely(wlist))
+ __post_watch_notification(wlist, n, cred, id);
+}
+
+static inline void remove_watch_list(struct watch_list *wlist, u64 id)
+{
+ if (wlist) {
+ remove_watch_from_object(wlist, NULL, id, true);
+ kfree_rcu(wlist, rcu);
+ }
+}
+
+/**
+ * watch_sizeof - Calculate the information part of the size of a watch record,
+ * given the structure size.
+ */
+#define watch_sizeof(STRUCT) (sizeof(STRUCT) << WATCH_INFO_LENGTH__SHIFT)
+
+#endif
+
+#endif /* _LINUX_WATCH_QUEUE_H */
diff --git a/include/uapi/linux/watch_queue.h b/include/uapi/linux/watch_queue.h
index 9df72227f515..3a5790f1f05d 100644
--- a/include/uapi/linux/watch_queue.h
+++ b/include/uapi/linux/watch_queue.h
@@ -4,9 +4,13 @@
#include <linux/types.h>
#include <linux/fcntl.h>
+#include <linux/ioctl.h>
#define O_NOTIFICATION_PIPE O_EXCL /* Parameter to pipe2() selecting notification pipe */
+#define IOC_WATCH_QUEUE_SET_SIZE _IO('W', 0x60) /* Set the size in pages */
+#define IOC_WATCH_QUEUE_SET_FILTER _IO('W', 0x61) /* Set the filter */
+
enum watch_notification_type {
WATCH_TYPE_META = 0, /* Special record */
WATCH_TYPE__NR = 1
@@ -41,6 +45,22 @@ struct watch_notification {
#define WATCH_INFO_FLAG_7 0x00800000
};
+/*
+ * Notification filtering rules (IOC_WATCH_QUEUE_SET_FILTER).
+ */
+struct watch_notification_type_filter {
+ __u32 type; /* Type to apply filter to */
+ __u32 info_filter; /* Filter on watch_notification::info */
+ __u32 info_mask; /* Mask of relevant bits in info_filter */
+ __u32 subtype_filter[8]; /* Bitmask of subtypes to filter on */
+};
+
+struct watch_notification_filter {
+ __u32 nr_filters; /* Number of filters */
+ __u32 __reserved; /* Must be 0 */
+ struct watch_notification_type_filter filters[];
+};
+
/*
* Extended watch removal notification. This is used optionally if the type
diff --git a/init/Kconfig b/init/Kconfig
index cfee56c151f1..92229457dc7f 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -339,6 +339,18 @@ config POSIX_MQUEUE_SYSCTL
depends on SYSCTL
default y
+config WATCH_QUEUE
+ bool "General notification queue"
+ default n
+ help
+
+ This is a general notification queue for the kernel to pass events to
+ userspace by splicing them into pipes. It can be used in conjunction
+ with watches for key/keyring change notifications and device
+ notifications.
+
+ See Documentation/watch_queue.rst
+
config CROSS_MEMORY_ATTACH
bool "Enable process_vm_readv/writev syscalls"
depends on MMU
diff --git a/kernel/Makefile b/kernel/Makefile
index 4cb4130ced32..41e7e3ae07ec 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -115,6 +115,7 @@ obj-$(CONFIG_TORTURE_TEST) += torture.o
obj-$(CONFIG_HAS_IOMEM) += iomem.o
obj-$(CONFIG_RSEQ) += rseq.o
+obj-$(CONFIG_WATCH_QUEUE) += watch_queue.o
obj-$(CONFIG_SYSCTL_KUNIT_TEST) += sysctl-test.o
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
new file mode 100644
index 000000000000..c103e34f8705
--- /dev/null
+++ b/kernel/watch_queue.c
@@ -0,0 +1,657 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Watch queue and general notification mechanism, built on pipes
+ *
+ * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * See Documentation/watch_queue.rst
+ */
+
+#define pr_fmt(fmt) "watchq: " fmt
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/printk.h>
+#include <linux/miscdevice.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/poll.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/file.h>
+#include <linux/security.h>
+#include <linux/cred.h>
+#include <linux/sched/signal.h>
+#include <linux/watch_queue.h>
+#include <linux/pipe_fs_i.h>
+
+MODULE_DESCRIPTION("Watch queue");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+#define WATCH_QUEUE_NOTE_SIZE 128
+#define WATCH_QUEUE_NOTES_PER_PAGE (PAGE_SIZE / WATCH_QUEUE_NOTE_SIZE)
+
+static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ struct watch_queue *wqueue = (struct watch_queue *)buf->private;
+ struct page *page;
+ unsigned int bit;
+
+ /* We need to work out which note within the page this refers to, but
+ * the note might have been maximum size, so merely ANDing the offset
+ * off doesn't work. OTOH, the note must've been more than zero size.
+ */
+ bit = buf->offset + buf->len;
+ if ((bit & (WATCH_QUEUE_NOTE_SIZE - 1)) == 0)
+ bit -= WATCH_QUEUE_NOTE_SIZE;
+ bit /= WATCH_QUEUE_NOTE_SIZE;
+
+ page = buf->page;
+ bit += page->index;
+
+ set_bit(bit, wqueue->notes_bitmap);
+}
+
+static int watch_queue_pipe_buf_steal(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ return -1; /* No. */
+}
+
+/* New data written to a pipe may be appended to a buffer with this type. */
+static const struct pipe_buf_operations watch_queue_pipe_buf_ops = {
+ .confirm = generic_pipe_buf_confirm,
+ .release = watch_queue_pipe_buf_release,
+ .steal = watch_queue_pipe_buf_steal,
+ .get = generic_pipe_buf_get,
+};
+
+/*
+ * Post a notification to a watch queue.
+ */
+static bool post_one_notification(struct watch_queue *wqueue,
+ struct watch_notification *n)
+{
+ void *p;
+ struct pipe_inode_info *pipe = wqueue->pipe;
+ struct pipe_buffer *buf;
+ struct page *page;
+ unsigned int head, tail, mask, note, offset, len;
+ bool done = false;
+
+ if (!pipe)
+ return false;
+
+ spin_lock_irq(&pipe->rd_wait.lock);
+
+ if (wqueue->defunct)
+ goto out;
+
+ mask = pipe->ring_size - 1;
+ head = pipe->head;
+ tail = pipe->tail;
+ if (pipe_full(head, tail, pipe->ring_size))
+ goto lost;
+
+ note = find_first_bit(wqueue->notes_bitmap, wqueue->nr_notes);
+ if (note >= wqueue->nr_notes)
+ goto lost;
+
+ page = wqueue->notes[note / WATCH_QUEUE_NOTES_PER_PAGE];
+ offset = note % WATCH_QUEUE_NOTES_PER_PAGE * WATCH_QUEUE_NOTE_SIZE;
+ get_page(page);
+ len = n->info & WATCH_INFO_LENGTH;
+ p = kmap_atomic(page);
+ memcpy(p + offset, n, len);
+ kunmap_atomic(p);
+
+ buf = &pipe->bufs[head & mask];
+ buf->page = page;
+ buf->private = (unsigned long)wqueue;
+ buf->ops = &watch_queue_pipe_buf_ops;
+ buf->offset = offset;
+ buf->len = len;
+ buf->flags = 0;
+ pipe->head = head + 1;
+
+ if (!test_and_clear_bit(note, wqueue->notes_bitmap)) {
+ spin_unlock_irq(&pipe->rd_wait.lock);
+ BUG();
+ }
+ wake_up_interruptible_sync_poll_locked(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM);
+ done = true;
+
+out:
+ spin_unlock_irq(&pipe->rd_wait.lock);
+ if (done)
+ kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
+ return done;
+
+lost:
+ goto out;
+}
+
+/*
+ * Apply filter rules to a notification.
+ */
+static bool filter_watch_notification(const struct watch_filter *wf,
+ const struct watch_notification *n)
+{
+ const struct watch_type_filter *wt;
+ unsigned int st_bits = sizeof(wt->subtype_filter[0]) * 8;
+ unsigned int st_index = n->subtype / st_bits;
+ unsigned int st_bit = 1U << (n->subtype % st_bits);
+ int i;
+
+ if (!test_bit(n->type, wf->type_filter))
+ return false;
+
+ for (i = 0; i < wf->nr_filters; i++) {
+ wt = &wf->filters[i];
+ if (n->type == wt->type &&
+ (wt->subtype_filter[st_index] & st_bit) &&
+ (n->info & wt->info_mask) == wt->info_filter)
+ return true;
+ }
+
+ return false; /* If there is a filter, the default is to reject. */
+}
+
+/**
+ * __post_watch_notification - Post an event notification
+ * @wlist: The watch list to post the event to.
+ * @n: The notification record to post.
+ * @cred: The creds of the process that triggered the notification.
+ * @id: The ID to match on the watch.
+ *
+ * Post a notification of an event into a set of watch queues and let the users
+ * know.
+ *
+ * The size of the notification should be set in n->info & WATCH_INFO_LENGTH and
+ * should be in units of sizeof(*n).
+ */
+void __post_watch_notification(struct watch_list *wlist,
+ struct watch_notification *n,
+ const struct cred *cred,
+ u64 id)
+{
+ const struct watch_filter *wf;
+ struct watch_queue *wqueue;
+ struct watch *watch;
+
+ if (((n->info & WATCH_INFO_LENGTH) >> WATCH_INFO_LENGTH__SHIFT) == 0) {
+ WARN_ON(1);
+ return;
+ }
+
+ rcu_read_lock();
+
+ hlist_for_each_entry_rcu(watch, &wlist->watchers, list_node) {
+ if (watch->id != id)
+ continue;
+ n->info &= ~WATCH_INFO_ID;
+ n->info |= watch->info_id;
+
+ wqueue = rcu_dereference(watch->queue);
+ wf = rcu_dereference(wqueue->filter);
+ if (wf && !filter_watch_notification(wf, n))
+ continue;
+
+ if (security_post_notification(watch->cred, cred, n) < 0)
+ continue;
+
+ post_one_notification(wqueue, n);
+ }
+
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL(__post_watch_notification);
+
+/*
+ * Allocate sufficient pages to preallocation for the requested number of
+ * notifications.
+ */
+long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes)
+{
+ struct watch_queue *wqueue = pipe->watch_queue;
+ struct page **pages;
+ unsigned long *bitmap;
+ unsigned long user_bufs;
+ unsigned int bmsize;
+ int ret, i, nr_pages;
+
+ if (!wqueue)
+ return -ENODEV;
+ if (wqueue->notes)
+ return -EBUSY;
+
+ if (nr_notes < 1 ||
+ nr_notes > 512) /* TODO: choose a better hard limit */
+ return -EINVAL;
+
+ nr_pages = (nr_notes + WATCH_QUEUE_NOTES_PER_PAGE - 1);
+ nr_pages /= WATCH_QUEUE_NOTES_PER_PAGE;
+ user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_pages);
+
+ if (nr_pages > pipe->max_usage &&
+ (too_many_pipe_buffers_hard(user_bufs) ||
+ too_many_pipe_buffers_soft(user_bufs)) &&
+ pipe_is_unprivileged_user()) {
+ ret = -EPERM;
+ goto error;
+ }
+
+ ret = pipe_resize_ring(pipe, nr_notes);
+ if (ret < 0)
+ goto error;
+
+ pages = kcalloc(sizeof(struct page *), nr_pages, GFP_KERNEL);
+ if (!pages)
+ goto error;
+
+ for (i = 0; i < nr_pages; i++) {
+ pages[i] = alloc_page(GFP_KERNEL);
+ if (!pages[i])
+ goto error_p;
+ pages[i]->index = i * WATCH_QUEUE_NOTES_PER_PAGE;
+ }
+
+ bmsize = (nr_notes + BITS_PER_LONG - 1) / BITS_PER_LONG;
+ bmsize *= sizeof(unsigned long);
+ bitmap = kmalloc(bmsize, GFP_KERNEL);
+ if (!bitmap)
+ goto error_p;
+
+ memset(bitmap, 0xff, bmsize);
+ wqueue->notes = pages;
+ wqueue->notes_bitmap = bitmap;
+ wqueue->nr_pages = nr_pages;
+ wqueue->nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE;
+ return 0;
+
+error_p:
+ for (i = 0; i < nr_pages; i++)
+ __free_page(pages[i]);
+ kfree(pages);
+error:
+ (void) account_pipe_buffers(pipe->user, nr_pages, pipe->nr_accounted);
+ return ret;
+}
+
+/*
+ * Set the filter on a watch queue.
+ */
+long watch_queue_set_filter(struct pipe_inode_info *pipe,
+ struct watch_notification_filter __user *_filter)
+{
+ struct watch_notification_type_filter *tf;
+ struct watch_notification_filter filter;
+ struct watch_type_filter *q;
+ struct watch_filter *wfilter;
+ struct watch_queue *wqueue = pipe->watch_queue;
+ int ret, nr_filter = 0, i;
+
+ if (!wqueue)
+ return -ENODEV;
+
+ if (!_filter) {
+ /* Remove the old filter */
+ wfilter = NULL;
+ goto set;
+ }
+
+ /* Grab the user's filter specification */
+ if (copy_from_user(&filter, _filter, sizeof(filter)) != 0)
+ return -EFAULT;
+ if (filter.nr_filters == 0 ||
+ filter.nr_filters > 16 ||
+ filter.__reserved != 0)
+ return -EINVAL;
+
+ tf = memdup_user(_filter->filters, filter.nr_filters * sizeof(*tf));
+ if (IS_ERR(tf))
+ return PTR_ERR(tf);
+
+ ret = -EINVAL;
+ for (i = 0; i < filter.nr_filters; i++) {
+ if ((tf[i].info_filter & ~tf[i].info_mask) ||
+ tf[i].info_mask & WATCH_INFO_LENGTH)
+ goto err_filter;
+ /* Ignore any unknown types */
+ if (tf[i].type >= sizeof(wfilter->type_filter) * 8)
+ continue;
+ nr_filter++;
+ }
+
+ /* Now we need to build the internal filter from only the relevant
+ * user-specified filters.
+ */
+ ret = -ENOMEM;
+ wfilter = kzalloc(struct_size(wfilter, filters, nr_filter), GFP_KERNEL);
+ if (!wfilter)
+ goto err_filter;
+ wfilter->nr_filters = nr_filter;
+
+ q = wfilter->filters;
+ for (i = 0; i < filter.nr_filters; i++) {
+ if (tf[i].type >= sizeof(wfilter->type_filter) * BITS_PER_LONG)
+ continue;
+
+ q->type = tf[i].type;
+ q->info_filter = tf[i].info_filter;
+ q->info_mask = tf[i].info_mask;
+ q->subtype_filter[0] = tf[i].subtype_filter[0];
+ __set_bit(q->type, wfilter->type_filter);
+ q++;
+ }
+
+ kfree(tf);
+set:
+ pipe_lock(pipe);
+ wfilter = rcu_replace_pointer(wqueue->filter, wfilter,
+ lockdep_is_held(&pipe->mutex));
+ pipe_unlock(pipe);
+ if (wfilter)
+ kfree_rcu(wfilter, rcu);
+ return 0;
+
+err_filter:
+ kfree(tf);
+ return ret;
+}
+
+static void __put_watch_queue(struct kref *kref)
+{
+ struct watch_queue *wqueue =
+ container_of(kref, struct watch_queue, usage);
+ struct watch_filter *wfilter;
+ int i;
+
+ for (i = 0; i < wqueue->nr_pages; i++)
+ __free_page(wqueue->notes[i]);
+
+ wfilter = rcu_access_pointer(wqueue->filter);
+ if (wfilter)
+ kfree_rcu(wfilter, rcu);
+ kfree_rcu(wqueue, rcu);
+}
+
+/**
+ * put_watch_queue - Dispose of a ref on a watchqueue.
+ * @wqueue: The watch queue to unref.
+ */
+void put_watch_queue(struct watch_queue *wqueue)
+{
+ kref_put(&wqueue->usage, __put_watch_queue);
+}
+EXPORT_SYMBOL(put_watch_queue);
+
+static void free_watch(struct rcu_head *rcu)
+{
+ struct watch *watch = container_of(rcu, struct watch, rcu);
+
+ put_watch_queue(rcu_access_pointer(watch->queue));
+ put_cred(watch->cred);
+}
+
+static void __put_watch(struct kref *kref)
+{
+ struct watch *watch = container_of(kref, struct watch, usage);
+
+ call_rcu(&watch->rcu, free_watch);
+}
+
+/*
+ * Discard a watch.
+ */
+static void put_watch(struct watch *watch)
+{
+ kref_put(&watch->usage, __put_watch);
+}
+
+/**
+ * init_watch_queue - Initialise a watch
+ * @watch: The watch to initialise.
+ * @wqueue: The queue to assign.
+ *
+ * Initialise a watch and set the watch queue.
+ */
+void init_watch(struct watch *watch, struct watch_queue *wqueue)
+{
+ kref_init(&watch->usage);
+ INIT_HLIST_NODE(&watch->list_node);
+ INIT_HLIST_NODE(&watch->queue_node);
+ rcu_assign_pointer(watch->queue, wqueue);
+}
+
+/**
+ * add_watch_to_object - Add a watch on an object to a watch list
+ * @watch: The watch to add
+ * @wlist: The watch list to add to
+ *
+ * @watch->queue must have been set to point to the queue to post notifications
+ * to and the watch list of the object to be watched. @watch->cred must also
+ * have been set to the appropriate credentials and a ref taken on them.
+ *
+ * The caller must pin the queue and the list both and must hold the list
+ * locked against racing watch additions/removals.
+ */
+int add_watch_to_object(struct watch *watch, struct watch_list *wlist)
+{
+ struct watch_queue *wqueue = rcu_access_pointer(watch->queue);
+ struct watch *w;
+
+ hlist_for_each_entry(w, &wlist->watchers, list_node) {
+ struct watch_queue *wq = rcu_access_pointer(w->queue);
+ if (wqueue == wq && watch->id == w->id)
+ return -EBUSY;
+ }
+
+ watch->cred = get_current_cred();
+ rcu_assign_pointer(watch->watch_list, wlist);
+
+ spin_lock_bh(&wqueue->lock);
+ kref_get(&wqueue->usage);
+ kref_get(&watch->usage);
+ hlist_add_head(&watch->queue_node, &wqueue->watches);
+ spin_unlock_bh(&wqueue->lock);
+
+ hlist_add_head(&watch->list_node, &wlist->watchers);
+ return 0;
+}
+EXPORT_SYMBOL(add_watch_to_object);
+
+/**
+ * remove_watch_from_object - Remove a watch or all watches from an object.
+ * @wlist: The watch list to remove from
+ * @wq: The watch queue of interest (ignored if @all is true)
+ * @id: The ID of the watch to remove (ignored if @all is true)
+ * @all: True to remove all objects
+ *
+ * Remove a specific watch or all watches from an object. A notification is
+ * sent to the watcher to tell them that this happened.
+ */
+int remove_watch_from_object(struct watch_list *wlist, struct watch_queue *wq,
+ u64 id, bool all)
+{
+ struct watch_notification_removal n;
+ struct watch_queue *wqueue;
+ struct watch *watch;
+ int ret = -EBADSLT;
+
+ rcu_read_lock();
+
+again:
+ spin_lock(&wlist->lock);
+ hlist_for_each_entry(watch, &wlist->watchers, list_node) {
+ if (all ||
+ (watch->id == id && rcu_access_pointer(watch->queue) == wq))
+ goto found;
+ }
+ spin_unlock(&wlist->lock);
+ goto out;
+
+found:
+ ret = 0;
+ hlist_del_init_rcu(&watch->list_node);
+ rcu_assign_pointer(watch->watch_list, NULL);
+ spin_unlock(&wlist->lock);
+
+ /* We now own the reference on watch that used to belong to wlist. */
+
+ n.watch.type = WATCH_TYPE_META;
+ n.watch.subtype = WATCH_META_REMOVAL_NOTIFICATION;
+ n.watch.info = watch->info_id | watch_sizeof(n.watch);
+ n.id = id;
+ if (id != 0)
+ n.watch.info = watch->info_id | watch_sizeof(n);
+
+ wqueue = rcu_dereference(watch->queue);
+
+ /* We don't need the watch list lock for the next bit as RCU is
+ * protecting *wqueue from deallocation.
+ */
+ if (wqueue) {
+ post_one_notification(wqueue, &n.watch);
+
+ spin_lock_bh(&wqueue->lock);
+
+ if (!hlist_unhashed(&watch->queue_node)) {
+ hlist_del_init_rcu(&watch->queue_node);
+ put_watch(watch);
+ }
+
+ spin_unlock_bh(&wqueue->lock);
+ }
+
+ if (wlist->release_watch) {
+ void (*release_watch)(struct watch *);
+
+ release_watch = wlist->release_watch;
+ rcu_read_unlock();
+ (*release_watch)(watch);
+ rcu_read_lock();
+ }
+ put_watch(watch);
+
+ if (all && !hlist_empty(&wlist->watchers))
+ goto again;
+out:
+ rcu_read_unlock();
+ return ret;
+}
+EXPORT_SYMBOL(remove_watch_from_object);
+
+/*
+ * Remove all the watches that are contributory to a queue. This has the
+ * potential to race with removal of the watches by the destruction of the
+ * objects being watched or with the distribution of notifications.
+ */
+void watch_queue_clear(struct watch_queue *wqueue)
+{
+ struct watch_list *wlist;
+ struct watch *watch;
+ bool release;
+
+ rcu_read_lock();
+ spin_lock_bh(&wqueue->lock);
+
+ /* Prevent new additions and prevent notifications from happening */
+ wqueue->defunct = true;
+
+ while (!hlist_empty(&wqueue->watches)) {
+ watch = hlist_entry(wqueue->watches.first, struct watch, queue_node);
+ hlist_del_init_rcu(&watch->queue_node);
+ /* We now own a ref on the watch. */
+ spin_unlock_bh(&wqueue->lock);
+
+ /* We can't do the next bit under the queue lock as we need to
+ * get the list lock - which would cause a deadlock if someone
+ * was removing from the opposite direction at the same time or
+ * posting a notification.
+ */
+ wlist = rcu_dereference(watch->watch_list);
+ if (wlist) {
+ void (*release_watch)(struct watch *);
+
+ spin_lock(&wlist->lock);
+
+ release = !hlist_unhashed(&watch->list_node);
+ if (release) {
+ hlist_del_init_rcu(&watch->list_node);
+ rcu_assign_pointer(watch->watch_list, NULL);
+
+ /* We now own a second ref on the watch. */
+ }
+
+ release_watch = wlist->release_watch;
+ spin_unlock(&wlist->lock);
+
+ if (release) {
+ if (release_watch) {
+ rcu_read_unlock();
+ /* This might need to call dput(), so
+ * we have to drop all the locks.
+ */
+ (*release_watch)(watch);
+ rcu_read_lock();
+ }
+ put_watch(watch);
+ }
+ }
+
+ put_watch(watch);
+ spin_lock_bh(&wqueue->lock);
+ }
+
+ spin_unlock_bh(&wqueue->lock);
+ rcu_read_unlock();
+}
+
+/**
+ * get_watch_queue - Get a watch queue from its file descriptor.
+ * @fd: The fd to query.
+ */
+struct watch_queue *get_watch_queue(int fd)
+{
+ struct pipe_inode_info *pipe;
+ struct watch_queue *wqueue = ERR_PTR(-EINVAL);
+ struct fd f;
+
+ f = fdget(fd);
+ if (f.file) {
+ pipe = get_pipe_info(f.file, false);
+ if (pipe && pipe->watch_queue) {
+ wqueue = pipe->watch_queue;
+ kref_get(&wqueue->usage);
+ }
+ fdput(f);
+ }
+
+ return wqueue;
+}
+EXPORT_SYMBOL(get_watch_queue);
+
+/*
+ * Initialise a watch queue
+ */
+int watch_queue_init(struct pipe_inode_info *pipe)
+{
+ struct watch_queue *wqueue;
+
+ wqueue = kzalloc(sizeof(*wqueue), GFP_KERNEL);
+ if (!wqueue)
+ return -ENOMEM;
+
+ wqueue->pipe = pipe;
+ kref_init(&wqueue->usage);
+ spin_lock_init(&wqueue->lock);
+ INIT_HLIST_HEAD(&wqueue->watches);
+
+ pipe->watch_queue = wqueue;
+ return 0;
+}
^ permalink raw reply related
* [RFC PATCH 06/17] watch_queue: Add a key/keyring notification facility [ver #4]
From: David Howells @ 2020-03-09 12:18 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, dhowells, casey, sds, nicolas.dichtel, raven, christian,
andres, jlayton, dray, kzak, keyrings, linux-api, linux-fsdevel,
linux-security-module, linux-kernel
In-Reply-To: <158375623086.334846.16121725232323108842.stgit@warthog.procyon.org.uk>
Add a key/keyring change notification facility whereby notifications about
changes in key and keyring content and attributes can be received.
Firstly, an event queue needs to be created:
pipe2(fds, O_NOTIFICATION_PIPE);
ioctl(fds[1], IOC_WATCH_QUEUE_SET_SIZE, 256);
then a notification can be set up to report notifications via that queue:
struct watch_notification_filter filter = {
.nr_filters = 1,
.filters = {
[0] = {
.type = WATCH_TYPE_KEY_NOTIFY,
.subtype_filter[0] = UINT_MAX,
},
},
};
ioctl(fds[1], IOC_WATCH_QUEUE_SET_FILTER, &filter);
keyctl_watch_key(KEY_SPEC_SESSION_KEYRING, fds[1], 0x01);
After that, records will be placed into the queue when events occur in
which keys are changed in some way. Records are of the following format:
struct key_notification {
struct watch_notification watch;
__u32 key_id;
__u32 aux;
} *n;
Where:
n->watch.type will be WATCH_TYPE_KEY_NOTIFY.
n->watch.subtype will indicate the type of event, such as
NOTIFY_KEY_REVOKED.
n->watch.info & WATCH_INFO_LENGTH will indicate the length of the
record.
n->watch.info & WATCH_INFO_ID will be the second argument to
keyctl_watch_key(), shifted.
n->key will be the ID of the affected key.
n->aux will hold subtype-dependent information, such as the key
being linked into the keyring specified by n->key in the case of
NOTIFY_KEY_LINKED.
Note that it is permissible for event records to be of variable length -
or, at least, the length may be dependent on the subtype. Note also that
the queue can be shared between multiple notifications of various types.
Signed-off-by: David Howells <dhowells@redhat.com>
---
Documentation/security/keys/core.rst | 58 ++++++++++++++++++++
include/linux/key.h | 3 +
include/uapi/linux/keyctl.h | 2 +
include/uapi/linux/watch_queue.h | 28 +++++++++-
security/keys/Kconfig | 9 +++
security/keys/compat.c | 3 +
security/keys/gc.c | 5 ++
security/keys/internal.h | 30 ++++++++++
security/keys/key.c | 38 ++++++++-----
security/keys/keyctl.c | 99 +++++++++++++++++++++++++++++++++-
security/keys/keyring.c | 20 ++++---
security/keys/request_key.c | 4 +
12 files changed, 271 insertions(+), 28 deletions(-)
diff --git a/Documentation/security/keys/core.rst b/Documentation/security/keys/core.rst
index d9b0b859018b..0154721b20b2 100644
--- a/Documentation/security/keys/core.rst
+++ b/Documentation/security/keys/core.rst
@@ -833,6 +833,7 @@ The keyctl syscall functions are:
A process must have search permission on the key for this function to be
successful.
+
* Compute a Diffie-Hellman shared secret or public key::
long keyctl(KEYCTL_DH_COMPUTE, struct keyctl_dh_params *params,
@@ -1026,6 +1027,63 @@ The keyctl syscall functions are:
written into the output buffer. Verification returns 0 on success.
+ * Watch a key or keyring for changes::
+
+ long keyctl(KEYCTL_WATCH_KEY, key_serial_t key, int queue_fd,
+ const struct watch_notification_filter *filter);
+
+ This will set or remove a watch for changes on the specified key or
+ keyring.
+
+ "key" is the ID of the key to be watched.
+
+ "queue_fd" is a file descriptor referring to an open "/dev/watch_queue"
+ which manages the buffer into which notifications will be delivered.
+
+ "filter" is either NULL to remove a watch or a filter specification to
+ indicate what events are required from the key.
+
+ See Documentation/watch_queue.rst for more information.
+
+ Note that only one watch may be emplaced for any particular { key,
+ queue_fd } combination.
+
+ Notification records look like::
+
+ struct key_notification {
+ struct watch_notification watch;
+ __u32 key_id;
+ __u32 aux;
+ };
+
+ In this, watch::type will be "WATCH_TYPE_KEY_NOTIFY" and subtype will be
+ one of::
+
+ NOTIFY_KEY_INSTANTIATED
+ NOTIFY_KEY_UPDATED
+ NOTIFY_KEY_LINKED
+ NOTIFY_KEY_UNLINKED
+ NOTIFY_KEY_CLEARED
+ NOTIFY_KEY_REVOKED
+ NOTIFY_KEY_INVALIDATED
+ NOTIFY_KEY_SETATTR
+
+ Where these indicate a key being instantiated/rejected, updated, a link
+ being made in a keyring, a link being removed from a keyring, a keyring
+ being cleared, a key being revoked, a key being invalidated or a key
+ having one of its attributes changed (user, group, perm, timeout,
+ restriction).
+
+ If a watched key is deleted, a basic watch_notification will be issued
+ with "type" set to WATCH_TYPE_META and "subtype" set to
+ watch_meta_removal_notification. The watchpoint ID will be set in the
+ "info" field.
+
+ This needs to be configured by enabling:
+
+ "Provide key/keyring change notifications" (KEY_NOTIFICATIONS)
+
+
Kernel Services
===============
diff --git a/include/linux/key.h b/include/linux/key.h
index 6cf8e71cf8b7..b99b40db08fc 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -176,6 +176,9 @@ struct key {
struct list_head graveyard_link;
struct rb_node serial_node;
};
+#ifdef CONFIG_KEY_NOTIFICATIONS
+ struct watch_list *watchers; /* Entities watching this key for changes */
+#endif
struct rw_semaphore sem; /* change vs change sem */
struct key_user *user; /* owner of this key */
void *security; /* security data for this key */
diff --git a/include/uapi/linux/keyctl.h b/include/uapi/linux/keyctl.h
index ed3d5893830d..4c8884eea808 100644
--- a/include/uapi/linux/keyctl.h
+++ b/include/uapi/linux/keyctl.h
@@ -69,6 +69,7 @@
#define KEYCTL_RESTRICT_KEYRING 29 /* Restrict keys allowed to link to a keyring */
#define KEYCTL_MOVE 30 /* Move keys between keyrings */
#define KEYCTL_CAPABILITIES 31 /* Find capabilities of keyrings subsystem */
+#define KEYCTL_WATCH_KEY 32 /* Watch a key or ring of keys for changes */
/* keyctl structures */
struct keyctl_dh_params {
@@ -130,5 +131,6 @@ struct keyctl_pkey_params {
#define KEYCTL_CAPS0_MOVE 0x80 /* KEYCTL_MOVE supported */
#define KEYCTL_CAPS1_NS_KEYRING_NAME 0x01 /* Keyring names are per-user_namespace */
#define KEYCTL_CAPS1_NS_KEY_TAG 0x02 /* Key indexing can include a namespace tag */
+#define KEYCTL_CAPS1_NOTIFICATIONS 0x04 /* Keys generate watchable notifications */
#endif /* _LINUX_KEYCTL_H */
diff --git a/include/uapi/linux/watch_queue.h b/include/uapi/linux/watch_queue.h
index 3a5790f1f05d..c3d8320b5d3a 100644
--- a/include/uapi/linux/watch_queue.h
+++ b/include/uapi/linux/watch_queue.h
@@ -13,7 +13,8 @@
enum watch_notification_type {
WATCH_TYPE_META = 0, /* Special record */
- WATCH_TYPE__NR = 1
+ WATCH_TYPE_KEY_NOTIFY = 1, /* Key change event notification */
+ WATCH_TYPE__NR = 2
};
enum watch_meta_notification_subtype {
@@ -75,4 +76,29 @@ struct watch_notification_removal {
__u64 id; /* Type-dependent identifier */
};
+/*
+ * Type of key/keyring change notification.
+ */
+enum key_notification_subtype {
+ NOTIFY_KEY_INSTANTIATED = 0, /* Key was instantiated (aux is error code) */
+ NOTIFY_KEY_UPDATED = 1, /* Key was updated */
+ NOTIFY_KEY_LINKED = 2, /* Key (aux) was added to watched keyring */
+ NOTIFY_KEY_UNLINKED = 3, /* Key (aux) was removed from watched keyring */
+ NOTIFY_KEY_CLEARED = 4, /* Keyring was cleared */
+ NOTIFY_KEY_REVOKED = 5, /* Key was revoked */
+ NOTIFY_KEY_INVALIDATED = 6, /* Key was invalidated */
+ NOTIFY_KEY_SETATTR = 7, /* Key's attributes got changed */
+};
+
+/*
+ * Key/keyring notification record.
+ * - watch.type = WATCH_TYPE_KEY_NOTIFY
+ * - watch.subtype = enum key_notification_type
+ */
+struct key_notification {
+ struct watch_notification watch;
+ __u32 key_id; /* The key/keyring affected */
+ __u32 aux; /* Per-type auxiliary data */
+};
+
#endif /* _UAPI_LINUX_WATCH_QUEUE_H */
diff --git a/security/keys/Kconfig b/security/keys/Kconfig
index 47c041563d41..d4dc5ea208af 100644
--- a/security/keys/Kconfig
+++ b/security/keys/Kconfig
@@ -116,3 +116,12 @@ config KEY_DH_OPERATIONS
in the kernel.
If you are unsure as to whether this is required, answer N.
+
+config KEY_NOTIFICATIONS
+ bool "Provide key/keyring change notifications"
+ depends on KEYS && WATCH_QUEUE
+ help
+ This option provides support for getting change notifications on keys
+ and keyrings on which the caller has View permission. This makes use
+ of the /dev/watch_queue misc device to handle the notification
+ buffer and provides KEYCTL_WATCH_KEY to enable/disable watches.
diff --git a/security/keys/compat.c b/security/keys/compat.c
index b975f8f11124..6ee9d8f6a4a5 100644
--- a/security/keys/compat.c
+++ b/security/keys/compat.c
@@ -156,6 +156,9 @@ COMPAT_SYSCALL_DEFINE5(keyctl, u32, option,
case KEYCTL_CAPABILITIES:
return keyctl_capabilities(compat_ptr(arg2), arg3);
+ case KEYCTL_WATCH_KEY:
+ return keyctl_watch_key(arg2, arg3, arg4);
+
default:
return -EOPNOTSUPP;
}
diff --git a/security/keys/gc.c b/security/keys/gc.c
index 671dd730ecfc..3c90807476eb 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -131,6 +131,11 @@ static noinline void key_gc_unused_keys(struct list_head *keys)
kdebug("- %u", key->serial);
key_check(key);
+#ifdef CONFIG_KEY_NOTIFICATIONS
+ remove_watch_list(key->watchers, key->serial);
+ key->watchers = NULL;
+#endif
+
/* Throw away the key data if the key is instantiated */
if (state == KEY_IS_POSITIVE && key->type->destroy)
key->type->destroy(key);
diff --git a/security/keys/internal.h b/security/keys/internal.h
index ba3e2da14cef..2a230c665162 100644
--- a/security/keys/internal.h
+++ b/security/keys/internal.h
@@ -15,6 +15,7 @@
#include <linux/task_work.h>
#include <linux/keyctl.h>
#include <linux/refcount.h>
+#include <linux/watch_queue.h>
#include <linux/compat.h>
struct iovec;
@@ -97,7 +98,8 @@ extern int __key_link_begin(struct key *keyring,
const struct keyring_index_key *index_key,
struct assoc_array_edit **_edit);
extern int __key_link_check_live_key(struct key *keyring, struct key *key);
-extern void __key_link(struct key *key, struct assoc_array_edit **_edit);
+extern void __key_link(struct key *keyring, struct key *key,
+ struct assoc_array_edit **_edit);
extern void __key_link_end(struct key *keyring,
const struct keyring_index_key *index_key,
struct assoc_array_edit *edit);
@@ -181,6 +183,23 @@ extern int key_task_permission(const key_ref_t key_ref,
const struct cred *cred,
key_perm_t perm);
+static inline void notify_key(struct key *key,
+ enum key_notification_subtype subtype, u32 aux)
+{
+#ifdef CONFIG_KEY_NOTIFICATIONS
+ struct key_notification n = {
+ .watch.type = WATCH_TYPE_KEY_NOTIFY,
+ .watch.subtype = subtype,
+ .watch.info = watch_sizeof(n),
+ .key_id = key_serial(key),
+ .aux = aux,
+ };
+
+ post_watch_notification(key->watchers, &n.watch, current_cred(),
+ n.key_id);
+#endif
+}
+
/*
* Check to see whether permission is granted to use a key in the desired way.
*/
@@ -331,6 +350,15 @@ static inline long keyctl_pkey_e_d_s(int op,
extern long keyctl_capabilities(unsigned char __user *_buffer, size_t buflen);
+#ifdef CONFIG_KEY_NOTIFICATIONS
+extern long keyctl_watch_key(key_serial_t, int, int);
+#else
+static inline long keyctl_watch_key(key_serial_t key_id, int watch_fd, int watch_id)
+{
+ return -EOPNOTSUPP;
+}
+#endif
+
/*
* Debugging key validation
*/
diff --git a/security/keys/key.c b/security/keys/key.c
index 718bf7217420..59b19268dca4 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -444,6 +444,7 @@ static int __key_instantiate_and_link(struct key *key,
/* mark the key as being instantiated */
atomic_inc(&key->user->nikeys);
mark_key_instantiated(key, 0);
+ notify_key(key, NOTIFY_KEY_INSTANTIATED, 0);
if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags))
awaken = 1;
@@ -453,7 +454,7 @@ static int __key_instantiate_and_link(struct key *key,
if (test_bit(KEY_FLAG_KEEP, &keyring->flags))
set_bit(KEY_FLAG_KEEP, &key->flags);
- __key_link(key, _edit);
+ __key_link(keyring, key, _edit);
}
/* disable the authorisation key */
@@ -601,6 +602,7 @@ int key_reject_and_link(struct key *key,
/* mark the key as being negatively instantiated */
atomic_inc(&key->user->nikeys);
mark_key_instantiated(key, -error);
+ notify_key(key, NOTIFY_KEY_INSTANTIATED, -error);
key->expiry = ktime_get_real_seconds() + timeout;
key_schedule_gc(key->expiry + key_gc_delay);
@@ -611,7 +613,7 @@ int key_reject_and_link(struct key *key,
/* and link it into the destination keyring */
if (keyring && link_ret == 0)
- __key_link(key, &edit);
+ __key_link(keyring, key, &edit);
/* disable the authorisation key */
if (authkey)
@@ -764,9 +766,11 @@ static inline key_ref_t __key_update(key_ref_t key_ref,
down_write(&key->sem);
ret = key->type->update(key, prep);
- if (ret == 0)
+ if (ret == 0) {
/* Updating a negative key positively instantiates it */
mark_key_instantiated(key, 0);
+ notify_key(key, NOTIFY_KEY_UPDATED, 0);
+ }
up_write(&key->sem);
@@ -1023,9 +1027,11 @@ int key_update(key_ref_t key_ref, const void *payload, size_t plen)
down_write(&key->sem);
ret = key->type->update(key, &prep);
- if (ret == 0)
+ if (ret == 0) {
/* Updating a negative key positively instantiates it */
mark_key_instantiated(key, 0);
+ notify_key(key, NOTIFY_KEY_UPDATED, 0);
+ }
up_write(&key->sem);
@@ -1057,15 +1063,17 @@ void key_revoke(struct key *key)
* instantiated
*/
down_write_nested(&key->sem, 1);
- if (!test_and_set_bit(KEY_FLAG_REVOKED, &key->flags) &&
- key->type->revoke)
- key->type->revoke(key);
-
- /* set the death time to no more than the expiry time */
- time = ktime_get_real_seconds();
- if (key->revoked_at == 0 || key->revoked_at > time) {
- key->revoked_at = time;
- key_schedule_gc(key->revoked_at + key_gc_delay);
+ if (!test_and_set_bit(KEY_FLAG_REVOKED, &key->flags)) {
+ notify_key(key, NOTIFY_KEY_REVOKED, 0);
+ if (key->type->revoke)
+ key->type->revoke(key);
+
+ /* set the death time to no more than the expiry time */
+ time = ktime_get_real_seconds();
+ if (key->revoked_at == 0 || key->revoked_at > time) {
+ key->revoked_at = time;
+ key_schedule_gc(key->revoked_at + key_gc_delay);
+ }
}
up_write(&key->sem);
@@ -1087,8 +1095,10 @@ void key_invalidate(struct key *key)
if (!test_bit(KEY_FLAG_INVALIDATED, &key->flags)) {
down_write_nested(&key->sem, 1);
- if (!test_and_set_bit(KEY_FLAG_INVALIDATED, &key->flags))
+ if (!test_and_set_bit(KEY_FLAG_INVALIDATED, &key->flags)) {
+ notify_key(key, NOTIFY_KEY_INVALIDATED, 0);
key_schedule_gc_links();
+ }
up_write(&key->sem);
}
}
diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
index 9b898c969558..6610649514fb 100644
--- a/security/keys/keyctl.c
+++ b/security/keys/keyctl.c
@@ -37,7 +37,9 @@ static const unsigned char keyrings_capabilities[2] = {
KEYCTL_CAPS0_MOVE
),
[1] = (KEYCTL_CAPS1_NS_KEYRING_NAME |
- KEYCTL_CAPS1_NS_KEY_TAG),
+ KEYCTL_CAPS1_NS_KEY_TAG |
+ (IS_ENABLED(CONFIG_KEY_NOTIFICATIONS) ? KEYCTL_CAPS1_NOTIFICATIONS : 0)
+ ),
};
static int key_get_type_from_user(char *type,
@@ -970,6 +972,7 @@ long keyctl_chown_key(key_serial_t id, uid_t user, gid_t group)
if (group != (gid_t) -1)
key->gid = gid;
+ notify_key(key, NOTIFY_KEY_SETATTR, 0);
ret = 0;
error_put:
@@ -1020,6 +1023,7 @@ long keyctl_setperm_key(key_serial_t id, key_perm_t perm)
/* if we're not the sysadmin, we can only change a key that we own */
if (capable(CAP_SYS_ADMIN) || uid_eq(key->uid, current_fsuid())) {
key->perm = perm;
+ notify_key(key, NOTIFY_KEY_SETATTR, 0);
ret = 0;
}
@@ -1411,10 +1415,12 @@ long keyctl_set_timeout(key_serial_t id, unsigned timeout)
okay:
key = key_ref_to_ptr(key_ref);
ret = 0;
- if (test_bit(KEY_FLAG_KEEP, &key->flags))
+ if (test_bit(KEY_FLAG_KEEP, &key->flags)) {
ret = -EPERM;
- else
+ } else {
key_set_timeout(key, timeout);
+ notify_key(key, NOTIFY_KEY_SETATTR, 0);
+ }
key_put(key);
error:
@@ -1688,6 +1694,90 @@ long keyctl_restrict_keyring(key_serial_t id, const char __user *_type,
return ret;
}
+#ifdef CONFIG_KEY_NOTIFICATIONS
+/*
+ * Watch for changes to a key.
+ *
+ * The caller must have View permission to watch a key or keyring.
+ */
+long keyctl_watch_key(key_serial_t id, int watch_queue_fd, int watch_id)
+{
+ struct watch_queue *wqueue;
+ struct watch_list *wlist = NULL;
+ struct watch *watch = NULL;
+ struct key *key;
+ key_ref_t key_ref;
+ long ret;
+
+ if (watch_id < -1 || watch_id > 0xff)
+ return -EINVAL;
+
+ key_ref = lookup_user_key(id, KEY_LOOKUP_CREATE, KEY_NEED_VIEW);
+ if (IS_ERR(key_ref))
+ return PTR_ERR(key_ref);
+ key = key_ref_to_ptr(key_ref);
+
+ wqueue = get_watch_queue(watch_queue_fd);
+ if (IS_ERR(wqueue)) {
+ ret = PTR_ERR(wqueue);
+ goto err_key;
+ }
+
+ if (watch_id >= 0) {
+ ret = -ENOMEM;
+ if (!key->watchers) {
+ wlist = kzalloc(sizeof(*wlist), GFP_KERNEL);
+ if (!wlist)
+ goto err_wqueue;
+ init_watch_list(wlist, NULL);
+ }
+
+ watch = kzalloc(sizeof(*watch), GFP_KERNEL);
+ if (!watch)
+ goto err_wlist;
+
+ init_watch(watch, wqueue);
+ watch->id = key->serial;
+ watch->info_id = (u32)watch_id << WATCH_INFO_ID__SHIFT;
+
+ ret = security_watch_key(key);
+ if (ret < 0)
+ goto err_watch;
+
+ down_write(&key->sem);
+ if (!key->watchers) {
+ key->watchers = wlist;
+ wlist = NULL;
+ }
+
+ ret = add_watch_to_object(watch, key->watchers);
+ up_write(&key->sem);
+
+ if (ret == 0)
+ watch = NULL;
+ } else {
+ ret = -EBADSLT;
+ if (key->watchers) {
+ down_write(&key->sem);
+ ret = remove_watch_from_object(key->watchers,
+ wqueue, key_serial(key),
+ false);
+ up_write(&key->sem);
+ }
+ }
+
+err_watch:
+ kfree(watch);
+err_wlist:
+ kfree(wlist);
+err_wqueue:
+ put_watch_queue(wqueue);
+err_key:
+ key_put(key);
+ return ret;
+}
+#endif /* CONFIG_KEY_NOTIFICATIONS */
+
/*
* Get keyrings subsystem capabilities.
*/
@@ -1857,6 +1947,9 @@ SYSCALL_DEFINE5(keyctl, int, option, unsigned long, arg2, unsigned long, arg3,
case KEYCTL_CAPABILITIES:
return keyctl_capabilities((unsigned char __user *)arg2, (size_t)arg3);
+ case KEYCTL_WATCH_KEY:
+ return keyctl_watch_key((key_serial_t)arg2, (int)arg3, (int)arg4);
+
default:
return -EOPNOTSUPP;
}
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index febf36c6ddc5..40a0dcdfda44 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -1060,12 +1060,14 @@ int keyring_restrict(key_ref_t keyring_ref, const char *type,
down_write(&keyring->sem);
down_write(&keyring_serialise_restrict_sem);
- if (keyring->restrict_link)
+ if (keyring->restrict_link) {
ret = -EEXIST;
- else if (keyring_detect_restriction_cycle(keyring, restrict_link))
+ } else if (keyring_detect_restriction_cycle(keyring, restrict_link)) {
ret = -EDEADLK;
- else
+ } else {
keyring->restrict_link = restrict_link;
+ notify_key(keyring, NOTIFY_KEY_SETATTR, 0);
+ }
up_write(&keyring_serialise_restrict_sem);
up_write(&keyring->sem);
@@ -1366,12 +1368,14 @@ int __key_link_check_live_key(struct key *keyring, struct key *key)
* holds at most one link to any given key of a particular type+description
* combination.
*/
-void __key_link(struct key *key, struct assoc_array_edit **_edit)
+void __key_link(struct key *keyring, struct key *key,
+ struct assoc_array_edit **_edit)
{
__key_get(key);
assoc_array_insert_set_object(*_edit, keyring_key_to_ptr(key));
assoc_array_apply_edit(*_edit);
*_edit = NULL;
+ notify_key(keyring, NOTIFY_KEY_LINKED, key_serial(key));
}
/*
@@ -1455,7 +1459,7 @@ int key_link(struct key *keyring, struct key *key)
if (ret == 0)
ret = __key_link_check_live_key(keyring, key);
if (ret == 0)
- __key_link(key, &edit);
+ __key_link(keyring, key, &edit);
error_end:
__key_link_end(keyring, &key->index_key, edit);
@@ -1487,7 +1491,7 @@ static int __key_unlink_begin(struct key *keyring, struct key *key,
struct assoc_array_edit *edit;
BUG_ON(*_edit != NULL);
-
+
edit = assoc_array_delete(&keyring->keys, &keyring_assoc_array_ops,
&key->index_key);
if (IS_ERR(edit))
@@ -1507,6 +1511,7 @@ static void __key_unlink(struct key *keyring, struct key *key,
struct assoc_array_edit **_edit)
{
assoc_array_apply_edit(*_edit);
+ notify_key(keyring, NOTIFY_KEY_UNLINKED, key_serial(key));
*_edit = NULL;
key_payload_reserve(keyring, keyring->datalen - KEYQUOTA_LINK_BYTES);
}
@@ -1625,7 +1630,7 @@ int key_move(struct key *key,
goto error;
__key_unlink(from_keyring, key, &from_edit);
- __key_link(key, &to_edit);
+ __key_link(to_keyring, key, &to_edit);
error:
__key_link_end(to_keyring, &key->index_key, to_edit);
__key_unlink_end(from_keyring, key, from_edit);
@@ -1659,6 +1664,7 @@ int keyring_clear(struct key *keyring)
} else {
if (edit)
assoc_array_apply_edit(edit);
+ notify_key(keyring, NOTIFY_KEY_CLEARED, 0);
key_payload_reserve(keyring, 0);
ret = 0;
}
diff --git a/security/keys/request_key.c b/security/keys/request_key.c
index 957b9e3e1492..e1b9f1a80676 100644
--- a/security/keys/request_key.c
+++ b/security/keys/request_key.c
@@ -418,7 +418,7 @@ static int construct_alloc_key(struct keyring_search_context *ctx,
goto key_already_present;
if (dest_keyring)
- __key_link(key, &edit);
+ __key_link(dest_keyring, key, &edit);
mutex_unlock(&key_construction_mutex);
if (dest_keyring)
@@ -437,7 +437,7 @@ static int construct_alloc_key(struct keyring_search_context *ctx,
if (dest_keyring) {
ret = __key_link_check_live_key(dest_keyring, key);
if (ret == 0)
- __key_link(key, &edit);
+ __key_link(dest_keyring, key, &edit);
__key_link_end(dest_keyring, &ctx->index_key, edit);
if (ret < 0)
goto link_check_failed;
^ permalink raw reply related
* [RFC PATCH 07/17] Add sample notification program [ver #4]
From: David Howells @ 2020-03-09 12:18 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, dhowells, casey, sds, nicolas.dichtel, raven, christian,
andres, jlayton, dray, kzak, keyrings, linux-api, linux-fsdevel,
linux-security-module, linux-kernel
In-Reply-To: <158375623086.334846.16121725232323108842.stgit@warthog.procyon.org.uk>
The sample program is run like:
./samples/watch_queue/watch_test
and watches "/" for mount changes and the current session keyring for key
changes:
# keyctl add user a a @s
1035096409
# keyctl unlink 1035096409 @s
producing:
# ./watch_test
read() = 16
NOTIFY[000]: ty=000001 sy=02 i=00000110
KEY 2ffc2e5d change=2[linked] aux=1035096409
read() = 16
NOTIFY[000]: ty=000001 sy=02 i=00000110
KEY 2ffc2e5d change=3[unlinked] aux=1035096409
Other events may be produced, such as with a failing disk:
read() = 22
NOTIFY[000]: ty=000003 sy=02 i=00000416
USB 3-7.7 dev-reset e=0 r=0
read() = 24
NOTIFY[000]: ty=000002 sy=06 i=00000418
BLOCK 00800050 e=6[critical medium] s=64000ef8
This corresponds to:
blk_update_request: critical medium error, dev sdf, sector 1677725432 op 0x0:(READ) flags 0x0 phys_seg 1 prio class 0
in dmesg.
Signed-off-by: David Howells <dhowells@redhat.com>
---
samples/Kconfig | 6 +
samples/Makefile | 1
samples/watch_queue/Makefile | 7 +
samples/watch_queue/watch_test.c | 183 ++++++++++++++++++++++++++++++++++++++
4 files changed, 197 insertions(+)
create mode 100644 samples/watch_queue/Makefile
create mode 100644 samples/watch_queue/watch_test.c
diff --git a/samples/Kconfig b/samples/Kconfig
index 9d236c346de5..5c31971a5745 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -190,5 +190,11 @@ config SAMPLE_INTEL_MEI
help
Build a sample program to work with mei device.
+config SAMPLE_WATCH_QUEUE
+ bool "Build example /dev/watch_queue notification consumer"
+ depends on HEADERS_INSTALL
+ help
+ Build example userspace program to use the new mount_notify(),
+ sb_notify() syscalls and the KEYCTL_WATCH_KEY keyctl() function.
endif # SAMPLES
diff --git a/samples/Makefile b/samples/Makefile
index f8f847b4f61f..8617edf7f19a 100644
--- a/samples/Makefile
+++ b/samples/Makefile
@@ -24,3 +24,4 @@ obj-$(CONFIG_VIDEO_PCI_SKELETON) += v4l/
obj-y += vfio-mdev/
subdir-$(CONFIG_SAMPLE_VFS) += vfs
obj-$(CONFIG_SAMPLE_INTEL_MEI) += mei/
+subdir-$(CONFIG_SAMPLE_WATCH_QUEUE) += watch_queue
diff --git a/samples/watch_queue/Makefile b/samples/watch_queue/Makefile
new file mode 100644
index 000000000000..eec00dd0a8df
--- /dev/null
+++ b/samples/watch_queue/Makefile
@@ -0,0 +1,7 @@
+# List of programs to build
+hostprogs-y := watch_test
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+
+HOSTCFLAGS_watch_test.o += -I$(objtree)/usr/include
diff --git a/samples/watch_queue/watch_test.c b/samples/watch_queue/watch_test.c
new file mode 100644
index 000000000000..9bf60abf5c7e
--- /dev/null
+++ b/samples/watch_queue/watch_test.c
@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Use /dev/watch_queue to watch for notifications.
+ *
+ * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#define _GNU_SOURCE
+#include <stdbool.h>
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+#include <errno.h>
+#include <sys/ioctl.h>
+#include <limits.h>
+#include <linux/watch_queue.h>
+#include <linux/unistd.h>
+#include <linux/keyctl.h>
+
+#ifndef KEYCTL_WATCH_KEY
+#define KEYCTL_WATCH_KEY -1
+#endif
+#ifndef __NR_watch_devices
+#define __NR_watch_devices -1
+#endif
+
+#define BUF_SIZE 256
+
+static long keyctl_watch_key(int key, int watch_fd, int watch_id)
+{
+ return syscall(__NR_keyctl, KEYCTL_WATCH_KEY, key, watch_fd, watch_id);
+}
+
+static const char *key_subtypes[256] = {
+ [NOTIFY_KEY_INSTANTIATED] = "instantiated",
+ [NOTIFY_KEY_UPDATED] = "updated",
+ [NOTIFY_KEY_LINKED] = "linked",
+ [NOTIFY_KEY_UNLINKED] = "unlinked",
+ [NOTIFY_KEY_CLEARED] = "cleared",
+ [NOTIFY_KEY_REVOKED] = "revoked",
+ [NOTIFY_KEY_INVALIDATED] = "invalidated",
+ [NOTIFY_KEY_SETATTR] = "setattr",
+};
+
+static void saw_key_change(struct watch_notification *n, size_t len)
+{
+ struct key_notification *k = (struct key_notification *)n;
+
+ if (len != sizeof(struct key_notification)) {
+ fprintf(stderr, "Incorrect key message length\n");
+ return;
+ }
+
+ printf("KEY %08x change=%u[%s] aux=%u\n",
+ k->key_id, n->subtype, key_subtypes[n->subtype], k->aux);
+}
+
+/*
+ * Consume and display events.
+ */
+static void consumer(int fd)
+{
+ unsigned char buffer[4096], *p, *end;
+ union {
+ struct watch_notification n;
+ unsigned char buf1[128];
+ } n;
+ ssize_t buf_len;
+
+ for (;;) {
+ buf_len = read(fd, buffer, sizeof(buffer));
+ if (buf_len == -1) {
+ perror("read");
+ exit(1);
+ }
+
+ if (buf_len == 0) {
+ printf("-- END --\n");
+ return;
+ }
+
+ if (buf_len > sizeof(buffer)) {
+ fprintf(stderr, "Read buffer overrun: %zd\n", buf_len);
+ return;
+ }
+
+ printf("read() = %zd\n", buf_len);
+
+ p = buffer;
+ end = buffer + buf_len;
+ while (p < end) {
+ size_t largest, len;
+
+ largest = end - p;
+ if (largest > 128)
+ largest = 128;
+ if (largest < sizeof(struct watch_notification)) {
+ fprintf(stderr, "Short message header: %zu\n", largest);
+ return;
+ }
+ memcpy(&n, p, largest);
+
+ printf("NOTIFY[%03zx]: ty=%06x sy=%02x i=%08x\n",
+ p - buffer, n.n.type, n.n.subtype, n.n.info);
+
+ len = n.n.info & WATCH_INFO_LENGTH;
+ if (len < sizeof(n.n) || len > largest) {
+ fprintf(stderr, "Bad message length: %zu/%zu\n", len, largest);
+ exit(1);
+ }
+
+ switch (n.n.type) {
+ case WATCH_TYPE_META:
+ switch (n.n.subtype) {
+ case WATCH_META_REMOVAL_NOTIFICATION:
+ printf("REMOVAL of watchpoint %08x\n",
+ (n.n.info & WATCH_INFO_ID) >>
+ WATCH_INFO_ID__SHIFT);
+ break;
+ default:
+ printf("other meta record\n");
+ break;
+ }
+ break;
+ case WATCH_TYPE_KEY_NOTIFY:
+ saw_key_change(&n.n, len);
+ break;
+ default:
+ printf("other type\n");
+ break;
+ }
+
+ p += len;
+ }
+ }
+}
+
+static struct watch_notification_filter filter = {
+ .nr_filters = 1,
+ .filters = {
+ [0] = {
+ .type = WATCH_TYPE_KEY_NOTIFY,
+ .subtype_filter[0] = UINT_MAX,
+ },
+ },
+};
+
+int main(int argc, char **argv)
+{
+ int pipefd[2], fd;
+
+ if (pipe2(pipefd, O_NOTIFICATION_PIPE) == -1) {
+ perror("pipe2");
+ exit(1);
+ }
+ fd = pipefd[0];
+
+ if (ioctl(fd, IOC_WATCH_QUEUE_SET_SIZE, BUF_SIZE) == -1) {
+ perror("/dev/watch_queue(size)");
+ exit(1);
+ }
+
+ if (ioctl(fd, IOC_WATCH_QUEUE_SET_FILTER, &filter) == -1) {
+ perror("/dev/watch_queue(filter)");
+ exit(1);
+ }
+
+ if (keyctl_watch_key(KEY_SPEC_SESSION_KEYRING, fd, 0x01) == -1) {
+ perror("keyctl");
+ exit(1);
+ }
+
+ if (keyctl_watch_key(KEY_SPEC_USER_KEYRING, fd, 0x02) == -1) {
+ perror("keyctl");
+ exit(1);
+ }
+
+ consumer(fd);
+ exit(0);
+}
^ permalink raw reply related
* [RFC PATCH 08/17] pipe: Allow buffers to be marked read-whole-or-error for notifications [ver #4]
From: David Howells @ 2020-03-09 12:18 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, dhowells, casey, sds, nicolas.dichtel, raven, christian,
andres, jlayton, dray, kzak, keyrings, linux-api, linux-fsdevel,
linux-security-module, linux-kernel
In-Reply-To: <158375623086.334846.16121725232323108842.stgit@warthog.procyon.org.uk>
Allow a buffer to be marked such that read() must return the entire buffer
in one go or return ENOBUFS. Multiple buffers can be amalgamated into a
single read, but a short read will occur if the next "whole" buffer won't
fit.
This is useful for watch queue notifications to make sure we don't split a
notification across multiple reads, especially given that we need to
fabricate an overrun record under some circumstances - and that isn't in
the buffers.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/pipe.c | 8 +++++++-
include/linux/pipe_fs_i.h | 1 +
kernel/watch_queue.c | 2 +-
samples/watch_queue/watch_test.c | 2 +-
4 files changed, 10 insertions(+), 3 deletions(-)
diff --git a/fs/pipe.c b/fs/pipe.c
index 36eedf8cb143..c98452868dde 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -320,8 +320,14 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
size_t written;
int error;
- if (chars > total_len)
+ if (chars > total_len) {
+ if (buf->flags & PIPE_BUF_FLAG_WHOLE) {
+ if (ret == 0)
+ ret = -ENOBUFS;
+ break;
+ }
chars = total_len;
+ }
error = pipe_buf_confirm(pipe, buf);
if (error) {
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 8cd14d72dfd1..fee90981ba40 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -8,6 +8,7 @@
#define PIPE_BUF_FLAG_ATOMIC 0x02 /* was atomically mapped */
#define PIPE_BUF_FLAG_GIFT 0x04 /* page is a gift */
#define PIPE_BUF_FLAG_PACKET 0x08 /* read() as a packet */
+#define PIPE_BUF_FLAG_WHOLE 0x10 /* read() must return entire buffer or error */
/**
* struct pipe_buffer - a linux kernel pipe buffer
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index c103e34f8705..ad64ea300f6d 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -115,7 +115,7 @@ static bool post_one_notification(struct watch_queue *wqueue,
buf->ops = &watch_queue_pipe_buf_ops;
buf->offset = offset;
buf->len = len;
- buf->flags = 0;
+ buf->flags = PIPE_BUF_FLAG_WHOLE;
pipe->head = head + 1;
if (!test_and_clear_bit(note, wqueue->notes_bitmap)) {
diff --git a/samples/watch_queue/watch_test.c b/samples/watch_queue/watch_test.c
index 9bf60abf5c7e..924e13a49c37 100644
--- a/samples/watch_queue/watch_test.c
+++ b/samples/watch_queue/watch_test.c
@@ -63,7 +63,7 @@ static void saw_key_change(struct watch_notification *n, size_t len)
*/
static void consumer(int fd)
{
- unsigned char buffer[4096], *p, *end;
+ unsigned char buffer[433], *p, *end;
union {
struct watch_notification n;
unsigned char buf1[128];
^ permalink raw reply related
* [RFC PATCH 09/17] pipe: Add notification lossage handling [ver #4]
From: David Howells @ 2020-03-09 12:18 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, dhowells, casey, sds, nicolas.dichtel, raven, christian,
andres, jlayton, dray, kzak, keyrings, linux-api, linux-fsdevel,
linux-security-module, linux-kernel
In-Reply-To: <158375623086.334846.16121725232323108842.stgit@warthog.procyon.org.uk>
Add handling for loss of notifications by having read() insert a
loss-notification message after it has read the pipe buffer that was last
in the ring when the loss occurred.
Lossage can come about either by running out of notification descriptors or
by running out of space in the pipe ring.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/pipe.c | 28 ++++++++++++++++++++++++++++
include/linux/pipe_fs_i.h | 7 +++++++
kernel/watch_queue.c | 2 ++
samples/watch_queue/watch_test.c | 3 +++
4 files changed, 40 insertions(+)
diff --git a/fs/pipe.c b/fs/pipe.c
index c98452868dde..238601a7ab24 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -314,6 +314,30 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
unsigned int tail = pipe->tail;
unsigned int mask = pipe->ring_size - 1;
+#ifdef CONFIG_WATCH_QUEUE
+ if (pipe->note_loss) {
+ struct watch_notification n;
+
+ if (total_len < 8) {
+ if (ret == 0)
+ ret = -ENOBUFS;
+ break;
+ }
+
+ n.type = WATCH_TYPE_META;
+ n.subtype = WATCH_META_LOSS_NOTIFICATION;
+ n.info = watch_sizeof(n);
+ if (copy_to_iter(&n, sizeof(n), to) != sizeof(n)) {
+ if (ret == 0)
+ ret = -EFAULT;
+ break;
+ }
+ ret += sizeof(n);
+ total_len -= sizeof(n);
+ pipe->note_loss = false;
+ }
+#endif
+
if (!pipe_empty(head, tail)) {
struct pipe_buffer *buf = &pipe->bufs[tail & mask];
size_t chars = buf->len;
@@ -355,6 +379,10 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
if (!buf->len) {
pipe_buf_release(pipe, buf);
spin_lock_irq(&pipe->rd_wait.lock);
+#ifdef CONFIG_WATCH_QUEUE
+ if (buf->flags & PIPE_BUF_FLAG_LOSS)
+ pipe->note_loss = true;
+#endif
tail++;
pipe->tail = tail;
spin_unlock_irq(&pipe->rd_wait.lock);
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index fee90981ba40..50a4cfee36e2 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -9,6 +9,9 @@
#define PIPE_BUF_FLAG_GIFT 0x04 /* page is a gift */
#define PIPE_BUF_FLAG_PACKET 0x08 /* read() as a packet */
#define PIPE_BUF_FLAG_WHOLE 0x10 /* read() must return entire buffer or error */
+#ifdef CONFIG_WATCH_QUEUE
+#define PIPE_BUF_FLAG_LOSS 0x20 /* Message loss happened after this buffer */
+#endif
/**
* struct pipe_buffer - a linux kernel pipe buffer
@@ -33,6 +36,7 @@ struct pipe_buffer {
* @wait: reader/writer wait point in case of empty/full pipe
* @head: The point of buffer production
* @tail: The point of buffer consumption
+ * @note_loss: The next read() should insert a data-lost message
* @max_usage: The maximum number of slots that may be used in the ring
* @ring_size: total number of buffers (should be a power of 2)
* @nr_accounted: The amount this pipe accounts for in user->pipe_bufs
@@ -55,6 +59,9 @@ struct pipe_inode_info {
unsigned int tail;
unsigned int max_usage;
unsigned int ring_size;
+#ifdef CONFIG_WATCH_QUEUE
+ bool note_loss;
+#endif
unsigned int nr_accounted;
unsigned int readers;
unsigned int writers;
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index ad64ea300f6d..9a9699c06709 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -132,6 +132,8 @@ static bool post_one_notification(struct watch_queue *wqueue,
return done;
lost:
+ buf = &pipe->bufs[(head - 1) & mask];
+ buf->flags |= PIPE_BUF_FLAG_LOSS;
goto out;
}
diff --git a/samples/watch_queue/watch_test.c b/samples/watch_queue/watch_test.c
index 924e13a49c37..0eaff5dc04c3 100644
--- a/samples/watch_queue/watch_test.c
+++ b/samples/watch_queue/watch_test.c
@@ -120,6 +120,9 @@ static void consumer(int fd)
(n.n.info & WATCH_INFO_ID) >>
WATCH_INFO_ID__SHIFT);
break;
+ case WATCH_META_LOSS_NOTIFICATION:
+ printf("-- LOSS --\n");
+ break;
default:
printf("other meta record\n");
break;
^ permalink raw reply related
* [RFC PATCH 10/17] selinux: Implement the watch_key security hook [ver #4]
From: David Howells @ 2020-03-09 12:18 UTC (permalink / raw)
To: torvalds, viro
Cc: Stephen Smalley, dhowells, dhowells, casey, sds, nicolas.dichtel,
raven, christian, andres, jlayton, dray, kzak, keyrings,
linux-api, linux-fsdevel, linux-security-module, linux-kernel
In-Reply-To: <158375623086.334846.16121725232323108842.stgit@warthog.procyon.org.uk>
Implement the watch_key security hook to make sure that a key grants the
caller View permission in order to set a watch on a key.
For the moment, the watch_devices security hook is left unimplemented as
it's not obvious what the object should be since the queue is global and
didn't previously exist.
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Stephen Smalley <sds@tycho.nsa.gov>
---
security/selinux/hooks.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 4b6991e178d3..95be16d3f47a 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -6563,6 +6563,17 @@ static int selinux_key_getsecurity(struct key *key, char **_buffer)
*_buffer = context;
return rc;
}
+
+#ifdef CONFIG_KEY_NOTIFICATIONS
+static int selinux_watch_key(struct key *key)
+{
+ struct key_security_struct *ksec = key->security;
+ u32 sid = current_sid();
+
+ return avc_has_perm(&selinux_state,
+ sid, ksec->sid, SECCLASS_KEY, KEY_NEED_VIEW, NULL);
+}
+#endif
#endif
#ifdef CONFIG_SECURITY_INFINIBAND
@@ -7078,6 +7089,9 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = {
LSM_HOOK_INIT(key_free, selinux_key_free),
LSM_HOOK_INIT(key_permission, selinux_key_permission),
LSM_HOOK_INIT(key_getsecurity, selinux_key_getsecurity),
+#ifdef CONFIG_KEY_NOTIFICATIONS
+ LSM_HOOK_INIT(watch_key, selinux_watch_key),
+#endif
#endif
#ifdef CONFIG_AUDIT
^ permalink raw reply related
* [RFC PATCH 11/17] smack: Implement the watch_key and post_notification hooks [ver #4]
From: David Howells @ 2020-03-09 12:18 UTC (permalink / raw)
To: torvalds, viro
Cc: Casey Schaufler, dhowells, dhowells, casey, sds, nicolas.dichtel,
raven, christian, andres, jlayton, dray, kzak, keyrings,
linux-api, linux-fsdevel, linux-security-module, linux-kernel
In-Reply-To: <158375623086.334846.16121725232323108842.stgit@warthog.procyon.org.uk>
Implement the watch_key security hook in Smack to make sure that a key
grants the caller Read permission in order to set a watch on a key.
Also implement the post_notification security hook to make sure that the
notification source is granted Write permission by the watch queue.
For the moment, the watch_devices security hook is left unimplemented as
it's not obvious what the object should be since the queue is global and
didn't previously exist.
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Casey Schaufler <casey@schaufler-ca.com>
---
include/linux/lsm_audit.h | 1 +
security/smack/smack_lsm.c | 83 +++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 83 insertions(+), 1 deletion(-)
diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h
index 99d629fd9944..28f23b341c1c 100644
--- a/include/linux/lsm_audit.h
+++ b/include/linux/lsm_audit.h
@@ -75,6 +75,7 @@ struct common_audit_data {
#define LSM_AUDIT_DATA_IBPKEY 13
#define LSM_AUDIT_DATA_IBENDPORT 14
#define LSM_AUDIT_DATA_LOCKDOWN 15
+#define LSM_AUDIT_DATA_NOTIFICATION 16
union {
struct path path;
struct dentry *dentry;
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 8c61d175e195..2862fc383473 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -41,6 +41,7 @@
#include <linux/parser.h>
#include <linux/fs_context.h>
#include <linux/fs_parser.h>
+#include <linux/watch_queue.h>
#include "smack.h"
#define TRANS_TRUE "TRUE"
@@ -4265,7 +4266,7 @@ static int smack_key_permission(key_ref_t key_ref,
if (tkp == NULL)
return -EACCES;
- if (smack_privileged_cred(CAP_MAC_OVERRIDE, cred))
+ if (smack_privileged(CAP_MAC_OVERRIDE))
return 0;
#ifdef CONFIG_AUDIT
@@ -4311,8 +4312,81 @@ static int smack_key_getsecurity(struct key *key, char **_buffer)
return length;
}
+
+#ifdef CONFIG_KEY_NOTIFICATIONS
+/**
+ * smack_watch_key - Smack access to watch a key for notifications.
+ * @key: The key to be watched
+ *
+ * Return 0 if the @watch->cred has permission to read from the key object and
+ * an error otherwise.
+ */
+static int smack_watch_key(struct key *key)
+{
+ struct smk_audit_info ad;
+ struct smack_known *tkp = smk_of_current();
+ int rc;
+
+ if (key == NULL)
+ return -EINVAL;
+ /*
+ * If the key hasn't been initialized give it access so that
+ * it may do so.
+ */
+ if (key->security == NULL)
+ return 0;
+ /*
+ * This should not occur
+ */
+ if (tkp == NULL)
+ return -EACCES;
+
+ if (smack_privileged_cred(CAP_MAC_OVERRIDE, current_cred()))
+ return 0;
+
+#ifdef CONFIG_AUDIT
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_KEY);
+ ad.a.u.key_struct.key = key->serial;
+ ad.a.u.key_struct.key_desc = key->description;
+#endif
+ rc = smk_access(tkp, key->security, MAY_READ, &ad);
+ rc = smk_bu_note("key watch", tkp, key->security, MAY_READ, rc);
+ return rc;
+}
+#endif /* CONFIG_KEY_NOTIFICATIONS */
#endif /* CONFIG_KEYS */
+#ifdef CONFIG_WATCH_QUEUE
+/**
+ * smack_post_notification - Smack access to post a notification to a queue
+ * @w_cred: The credentials of the watcher.
+ * @cred: The credentials of the event source (may be NULL).
+ * @n: The notification message to be posted.
+ */
+static int smack_post_notification(const struct cred *w_cred,
+ const struct cred *cred,
+ struct watch_notification *n)
+{
+ struct smk_audit_info ad;
+ struct smack_known *subj, *obj;
+ int rc;
+
+ /* Always let maintenance notifications through. */
+ if (n->type == WATCH_TYPE_META)
+ return 0;
+
+ if (!cred)
+ return 0;
+ subj = smk_of_task(smack_cred(cred));
+ obj = smk_of_task(smack_cred(w_cred));
+
+ smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NOTIFICATION);
+ rc = smk_access(subj, obj, MAY_WRITE, &ad);
+ rc = smk_bu_note("notification", subj, obj, MAY_WRITE, rc);
+ return rc;
+}
+#endif /* CONFIG_WATCH_QUEUE */
+
/*
* Smack Audit hooks
*
@@ -4701,8 +4775,15 @@ static struct security_hook_list smack_hooks[] __lsm_ro_after_init = {
LSM_HOOK_INIT(key_free, smack_key_free),
LSM_HOOK_INIT(key_permission, smack_key_permission),
LSM_HOOK_INIT(key_getsecurity, smack_key_getsecurity),
+#ifdef CONFIG_KEY_NOTIFICATIONS
+ LSM_HOOK_INIT(watch_key, smack_watch_key),
+#endif
#endif /* CONFIG_KEYS */
+#ifdef CONFIG_WATCH_QUEUE
+ LSM_HOOK_INIT(post_notification, smack_post_notification),
+#endif
+
/* Audit hooks */
#ifdef CONFIG_AUDIT
LSM_HOOK_INIT(audit_rule_init, smack_audit_rule_init),
^ permalink raw reply related
* [RFC PATCH 12/17] watch_queue: Add security hooks to rule on setting mount and sb watches [ver #4]
From: David Howells @ 2020-03-09 12:19 UTC (permalink / raw)
To: torvalds, viro
Cc: Casey Schaufler, Stephen Smalley, linux-security-module, dhowells,
dhowells, casey, sds, nicolas.dichtel, raven, christian, andres,
jlayton, dray, kzak, keyrings, linux-api, linux-fsdevel,
linux-security-module, linux-kernel
In-Reply-To: <158375623086.334846.16121725232323108842.stgit@warthog.procyon.org.uk>
Add security hooks that will allow an LSM to rule on whether or not a watch
may be set on a mount or on a superblock. More than one hook is required
as the watches watch different types of object.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Casey Schaufler <casey@schaufler-ca.com>
cc: Stephen Smalley <sds@tycho.nsa.gov>
cc: linux-security-module@vger.kernel.org
---
include/linux/lsm_hooks.h | 24 ++++++++++++++++++++++++
include/linux/security.h | 16 ++++++++++++++++
security/security.c | 14 ++++++++++++++
3 files changed, 54 insertions(+)
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 16530255dc11..c4451ac197ae 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1427,6 +1427,18 @@
* Check to see if a process is allowed to watch for event notifications
* from devices (as a global set).
*
+ * @watch_mount:
+ * Check to see if a process is allowed to watch for mount topology change
+ * notifications on a mount subtree.
+ * @watch: The watch object
+ * @path: The root of the subtree to watch.
+ *
+ * @watch_sb:
+ * Check to see if a process is allowed to watch for event notifications
+ * from a superblock.
+ * @watch: The watch object
+ * @sb: The superblock to watch.
+ *
* @post_notification:
* Check to see if a watch notification can be posted to a particular
* queue.
@@ -1722,6 +1734,12 @@ union security_list_options {
#ifdef CONFIG_DEVICE_NOTIFICATIONS
int (*watch_devices)(void);
#endif
+#ifdef CONFIG_MOUNT_NOTIFICATIONS
+ int (*watch_mount)(struct watch *watch, struct path *path);
+#endif
+#ifdef CONFIG_SB_NOTIFICATIONS
+ int (*watch_sb)(struct watch *watch, struct super_block *sb);
+#endif
#ifdef CONFIG_WATCH_QUEUE
int (*post_notification)(const struct cred *w_cred,
const struct cred *cred,
@@ -2020,6 +2038,12 @@ struct security_hook_heads {
#ifdef CONFIG_DEVICE_NOTIFICATIONS
struct hlist_head watch_devices;
#endif
+#ifdef CONFIG_MOUNT_NOTIFICATIONS
+ struct hlist_head watch_mount;
+#endif
+#ifdef CONFIG_SB_NOTIFICATIONS
+ struct hlist_head watch_sb;
+#endif
#ifdef CONFIG_WATCH_QUEUE
struct hlist_head post_notification;
#endif /* CONFIG_WATCH_QUEUE */
diff --git a/include/linux/security.h b/include/linux/security.h
index 910a1efa9a79..2ca2569bc12c 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1306,6 +1306,22 @@ static inline int security_post_notification(const struct cred *w_cred,
return 0;
}
#endif
+#if defined(CONFIG_SECURITY) && defined(CONFIG_MOUNT_NOTIFICATIONS)
+int security_watch_mount(struct watch *watch, struct path *path);
+#else
+static inline int security_watch_mount(struct watch *watch, struct path *path)
+{
+ return 0;
+}
+#endif
+#if defined(CONFIG_SECURITY) && defined(CONFIG_SB_NOTIFICATIONS)
+int security_watch_sb(struct watch *watch, struct super_block *sb);
+#else
+static inline int security_watch_sb(struct watch *watch, struct super_block *sb)
+{
+ return 0;
+}
+#endif
#ifdef CONFIG_SECURITY_NETWORK
diff --git a/security/security.c b/security/security.c
index db7b574c9c70..5c0463444a90 100644
--- a/security/security.c
+++ b/security/security.c
@@ -2004,6 +2004,20 @@ int security_watch_key(struct key *key)
}
#endif
+#ifdef CONFIG_MOUNT_NOTIFICATIONS
+int security_watch_mount(struct watch *watch, struct path *path)
+{
+ return call_int_hook(watch_mount, 0, watch, path);
+}
+#endif
+
+#ifdef CONFIG_SB_NOTIFICATIONS
+int security_watch_sb(struct watch *watch, struct super_block *sb)
+{
+ return call_int_hook(watch_sb, 0, watch, sb);
+}
+#endif
+
#ifdef CONFIG_DEVICE_NOTIFICATIONS
int security_watch_devices(void)
{
^ permalink raw reply related
* [RFC PATCH 13/17] watch_queue: Implement mount topology and attribute change notifications [ver #4]
From: David Howells @ 2020-03-09 12:19 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, dhowells, casey, sds, nicolas.dichtel, raven, christian,
andres, jlayton, dray, kzak, keyrings, linux-api, linux-fsdevel,
linux-security-module, linux-kernel
In-Reply-To: <158375623086.334846.16121725232323108842.stgit@warthog.procyon.org.uk>
Add a mount notification facility whereby notifications about changes in
mount topology and configuration can be received. Note that this only
covers vfsmount topology changes and not superblock events. A separate
facility will be added for that.
Every mount is given a change counter than counts the number of topological
rearrangements in which it is involved and the number of attribute changes
it undergoes. This allows notification loss to be dealt with. Later
patches will provide a way to quickly retrieve this value, along with
information about topology and parameters for the superblock.
Firstly, a watch queue needs to be created:
pipe2(fds, O_NOTIFICATION_PIPE);
ioctl(fds[1], IOC_WATCH_QUEUE_SET_SIZE, 256);
then a notification can be set up to report notifications via that queue:
struct watch_notification_filter filter = {
.nr_filters = 1,
.filters = {
[0] = {
.type = WATCH_TYPE_MOUNT_NOTIFY,
.subtype_filter[0] = UINT_MAX,
},
},
};
ioctl(fds[1], IOC_WATCH_QUEUE_SET_FILTER, &filter);
watch_mount(AT_FDCWD, "/", 0, fds[1], 0x02);
In this case, it would let me monitor the mount topology subtree rooted at
"/" for events. Mount notifications propagate up the tree towards the
root, so a watch will catch all of the events happening in the subtree
rooted at the watch.
After setting the watch, records will be placed into the queue when, for
example, as superblock switches between read-write and read-only. Records
are of the following format:
struct mount_notification {
struct watch_notification watch;
__u32 triggered_on;
__u32 changed_mount;
} *n;
Where:
n->watch.type will be WATCH_TYPE_MOUNT_NOTIFY.
n->watch.subtype will indicate the type of event, such as
NOTIFY_MOUNT_NEW_MOUNT.
n->watch.info & WATCH_INFO_LENGTH will indicate the length of the
record.
n->watch.info & WATCH_INFO_ID will be the fifth argument to
watch_mount(), shifted.
n->watch.info & NOTIFY_MOUNT_IN_SUBTREE if true indicates that the
notifcation was generated in the mount subtree rooted at the watch,
and not actually in the watch itself.
n->watch.info & NOTIFY_MOUNT_IS_RECURSIVE if true indicates that
the notifcation was generated by an event (eg. SETATTR) that was
applied recursively. The notification is only generated for the
object that initially triggered it.
n->watch.info & NOTIFY_MOUNT_IS_NOW_RO will be used for
NOTIFY_MOUNT_READONLY, being set if the superblock becomes R/O, and
being cleared otherwise, and for NOTIFY_MOUNT_NEW_MOUNT, being set
if the new mount is a submount (e.g. an automount).
n->watch.info & NOTIFY_MOUNT_IS_SUBMOUNT if true indicates that the
NOTIFY_MOUNT_NEW_MOUNT notification is in response to a mount
performed by the kernel (e.g. an automount).
n->triggered_on indicates the ID of the mount on which the watch
was installed.
n->changed_mount indicates the ID of the mount that was affected.
Note that it is permissible for event records to be of variable length -
or, at least, the length may be dependent on the subtype. Note also that
the queue can be shared between multiple notifications of various types.
Signed-off-by: David Howells <dhowells@redhat.com>
---
arch/alpha/kernel/syscalls/syscall.tbl | 1
arch/arm/tools/syscall.tbl | 1
arch/arm64/include/asm/unistd.h | 2
arch/ia64/kernel/syscalls/syscall.tbl | 1
arch/m68k/kernel/syscalls/syscall.tbl | 1
arch/microblaze/kernel/syscalls/syscall.tbl | 1
arch/mips/kernel/syscalls/syscall_n32.tbl | 1
arch/mips/kernel/syscalls/syscall_n64.tbl | 1
arch/mips/kernel/syscalls/syscall_o32.tbl | 1
arch/parisc/kernel/syscalls/syscall.tbl | 1
arch/powerpc/kernel/syscalls/syscall.tbl | 1
arch/s390/kernel/syscalls/syscall.tbl | 1
arch/sh/kernel/syscalls/syscall.tbl | 1
arch/sparc/kernel/syscalls/syscall.tbl | 1
arch/x86/entry/syscalls/syscall_32.tbl | 1
arch/x86/entry/syscalls/syscall_64.tbl | 1
arch/xtensa/kernel/syscalls/syscall.tbl | 1
fs/Kconfig | 9 +
fs/Makefile | 1
fs/mount.h | 35 +++++
fs/mount_notify.c | 186 +++++++++++++++++++++++++++
fs/namespace.c | 22 +++
include/linux/dcache.h | 1
include/linux/syscalls.h | 2
include/uapi/asm-generic/unistd.h | 4 -
include/uapi/linux/watch_queue.h | 32 +++++
kernel/sys_ni.c | 3
27 files changed, 310 insertions(+), 3 deletions(-)
create mode 100644 fs/mount_notify.c
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 36d42da7466a..b869428033ef 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -477,3 +477,4 @@
# 545 reserved for clone3
547 common openat2 sys_openat2
548 common pidfd_getfd sys_pidfd_getfd
+549 common watch_mount sys_watch_mount
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 4d1cf74a2caa..9c389da9efcc 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -451,3 +451,4 @@
435 common clone3 sys_clone3
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
+439 common watch_mount sys_watch_mount
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 1dd22da1c3a9..75f04a1023be 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -38,7 +38,7 @@
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5)
#define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 439
+#define __NR_compat_syscalls 440
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index 042911e670b8..6817f865cc71 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -358,3 +358,4 @@
# 435 reserved for clone3
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
+439 common watch_mount sys_watch_mount
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index f4f49fcb76d0..fbf85da75ecb 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -437,3 +437,4 @@
435 common clone3 __sys_clone3
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
+439 common watch_mount sys_watch_mount
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 4c67b11f9c9e..b05b192da1e2 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -443,3 +443,4 @@
435 common clone3 sys_clone3
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
+439 common watch_mount sys_watch_mount
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 1f9e8ad636cc..0f85d2a033f9 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -376,3 +376,4 @@
435 n32 clone3 __sys_clone3
437 n32 openat2 sys_openat2
438 n32 pidfd_getfd sys_pidfd_getfd
+439 n32 watch_mount sys_watch_mount
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index c0b9d802dbf6..905cf9ac0792 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -352,3 +352,4 @@
435 n64 clone3 __sys_clone3
437 n64 openat2 sys_openat2
438 n64 pidfd_getfd sys_pidfd_getfd
+439 n64 watch_mount sys_watch_mount
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index ac586774c980..834b26b08d74 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -425,3 +425,4 @@
435 o32 clone3 __sys_clone3
437 o32 openat2 sys_openat2
438 o32 pidfd_getfd sys_pidfd_getfd
+439 o32 watch_mount sys_watch_mount
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index 52a15f5cd130..badd3449db43 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -435,3 +435,4 @@
435 common clone3 sys_clone3_wrapper
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
+439 common watch_mount sys_watch_mount
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 35b61bfc1b1a..b404361bc929 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -519,3 +519,4 @@
435 nospu clone3 ppc_clone3
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
+439 common watch_mount sys_watch_mount
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index bd7bd3581a0f..33071de24511 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -440,3 +440,4 @@
435 common clone3 sys_clone3 sys_clone3
437 common openat2 sys_openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd
+439 common watch_mount sys_watch_mount sys_watch_mount
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index c7a30fcd135f..682c125122f4 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -440,3 +440,4 @@
# 435 reserved for clone3
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
+439 common watch_mount sys_watch_mount
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index f13615ecdecc..febf3cd675e3 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -483,3 +483,4 @@
# 435 reserved for clone3
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
+439 common watch_mount sys_watch_mount
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index c17cb77eb150..085bcc5afdf1 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -442,3 +442,4 @@
435 i386 clone3 sys_clone3 __ia32_sys_clone3
437 i386 openat2 sys_openat2 __ia32_sys_openat2
438 i386 pidfd_getfd sys_pidfd_getfd __ia32_sys_pidfd_getfd
+439 i386 watch_mount sys_watch_mount __ia32_sys_watch_mount
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 44d510bc9b78..9cfb6b2eb319 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -359,6 +359,7 @@
435 common clone3 __x64_sys_clone3/ptregs
437 common openat2 __x64_sys_openat2
438 common pidfd_getfd __x64_sys_pidfd_getfd
+439 common watch_mount __x64_sys_watch_mount
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 85a9ab1bc04d..1a066a43a58b 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -408,3 +408,4 @@
435 common clone3 sys_clone3
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
+439 common watch_mount sys_watch_mount
diff --git a/fs/Kconfig b/fs/Kconfig
index 708ba336e689..d7039137d538 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -117,6 +117,15 @@ source "fs/verity/Kconfig"
source "fs/notify/Kconfig"
+config MOUNT_NOTIFICATIONS
+ bool "Mount topology change notifications"
+ select WATCH_QUEUE
+ help
+ This option provides support for getting change notifications on the
+ mount tree topology. This makes use of the /dev/watch_queue misc
+ device to handle the notification buffer and provides the
+ mount_notify() system call to enable/disable watchpoints.
+
source "fs/quota/Kconfig"
source "fs/autofs/Kconfig"
diff --git a/fs/Makefile b/fs/Makefile
index 505e51166973..4477757780d0 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -22,6 +22,7 @@ obj-y += no-block.o
endif
obj-$(CONFIG_PROC_FS) += proc_namespace.o
+obj-$(CONFIG_MOUNT_NOTIFICATIONS) += mount_notify.o
obj-y += notify/
obj-$(CONFIG_EPOLL) += eventpoll.o
diff --git a/fs/mount.h b/fs/mount.h
index 711a4093e475..381f842f3a27 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -4,6 +4,7 @@
#include <linux/poll.h>
#include <linux/ns_common.h>
#include <linux/fs_pin.h>
+#include <linux/watch_queue.h>
struct mnt_namespace {
atomic_t count;
@@ -72,6 +73,12 @@ struct mount {
int mnt_expiry_mark; /* true if marked for expiry */
struct hlist_head mnt_pins;
struct hlist_head mnt_stuck_children;
+#ifdef CONFIG_MOUNT_NOTIFICATIONS
+ atomic_t mnt_topology_changes; /* Number of topology changes applied */
+ atomic_t mnt_attr_changes; /* Number of attribute changes applied */
+ atomic_t mnt_subtree_notifications; /* Number of notifications in subtree */
+ struct watch_list *mnt_watchers; /* Watches on dentries within this mount */
+#endif
} __randomize_layout;
#define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */
@@ -153,3 +160,31 @@ static inline bool is_anon_ns(struct mnt_namespace *ns)
{
return ns->seq == 0;
}
+
+extern void post_mount_notification(struct mount *changed,
+ struct mount_notification *notify);
+
+static inline void notify_mount(struct mount *changed,
+ struct mount *aux,
+ enum mount_notification_subtype subtype,
+ u32 info_flags)
+{
+#ifdef CONFIG_MOUNT_NOTIFICATIONS
+ if (aux)
+ atomic_inc(&changed->mnt_topology_changes);
+ else
+ atomic_inc(&changed->mnt_attr_changes);
+
+ {
+ struct mount_notification n = {
+ .watch.type = WATCH_TYPE_MOUNT_NOTIFY,
+ .watch.subtype = subtype,
+ .watch.info = info_flags | watch_sizeof(n),
+ .triggered_on = changed->mnt_id,
+ .changed_mount = aux ? aux->mnt_id : 0,
+ };
+
+ post_mount_notification(changed, &n);
+ }
+#endif
+}
diff --git a/fs/mount_notify.c b/fs/mount_notify.c
new file mode 100644
index 000000000000..d946765afcc4
--- /dev/null
+++ b/fs/mount_notify.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Provide mount topology/attribute change notifications.
+ *
+ * Copyright (C) 2019 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/fs.h>
+#include <linux/namei.h>
+#include <linux/syscalls.h>
+#include <linux/slab.h>
+#include <linux/security.h>
+#include "mount.h"
+
+/*
+ * Post mount notifications to all watches going rootwards along the tree.
+ *
+ * Must be called with the mount_lock held.
+ */
+void post_mount_notification(struct mount *changed,
+ struct mount_notification *notify)
+{
+ const struct cred *cred = current_cred();
+ struct path cursor;
+ struct mount *mnt;
+ unsigned seq;
+
+ seq = 0;
+ rcu_read_lock();
+restart:
+ cursor.mnt = &changed->mnt;
+ cursor.dentry = changed->mnt.mnt_root;
+ mnt = real_mount(cursor.mnt);
+ notify->watch.info &= ~NOTIFY_MOUNT_IN_SUBTREE;
+
+ read_seqbegin_or_lock(&rename_lock, &seq);
+ for (;;) {
+ if (mnt->mnt_watchers &&
+ !hlist_empty(&mnt->mnt_watchers->watchers)) {
+ if (cursor.dentry->d_flags & DCACHE_MOUNT_WATCH)
+ post_watch_notification(mnt->mnt_watchers,
+ ¬ify->watch, cred,
+ (unsigned long)cursor.dentry);
+ } else {
+ cursor.dentry = mnt->mnt.mnt_root;
+ }
+ notify->watch.info |= NOTIFY_MOUNT_IN_SUBTREE;
+
+ if (cursor.dentry == cursor.mnt->mnt_root ||
+ IS_ROOT(cursor.dentry)) {
+ struct mount *parent = READ_ONCE(mnt->mnt_parent);
+
+ /* Escaped? */
+ if (cursor.dentry != cursor.mnt->mnt_root)
+ break;
+
+ /* Global root? */
+ if (mnt == parent)
+ break;
+
+ cursor.dentry = READ_ONCE(mnt->mnt_mountpoint);
+ mnt = parent;
+ cursor.mnt = &mnt->mnt;
+ atomic_inc(&mnt->mnt_subtree_notifications);
+ } else {
+ cursor.dentry = cursor.dentry->d_parent;
+ }
+ }
+
+ if (need_seqretry(&rename_lock, seq)) {
+ seq = 1;
+ goto restart;
+ }
+
+ done_seqretry(&rename_lock, seq);
+ rcu_read_unlock();
+}
+
+static void release_mount_watch(struct watch *watch)
+{
+ struct dentry *dentry = (struct dentry *)(unsigned long)watch->id;
+
+ dput(dentry);
+}
+
+/**
+ * sys_watch_mount - Watch for mount topology/attribute changes
+ * @dfd: Base directory to pathwalk from or fd referring to mount.
+ * @filename: Path to mount to place the watch upon
+ * @at_flags: Pathwalk control flags
+ * @watch_fd: The watch queue to send notifications to.
+ * @watch_id: The watch ID to be placed in the notification (-1 to remove watch)
+ */
+SYSCALL_DEFINE5(watch_mount,
+ int, dfd,
+ const char __user *, filename,
+ unsigned int, at_flags,
+ int, watch_fd,
+ int, watch_id)
+{
+ struct watch_queue *wqueue;
+ struct watch_list *wlist = NULL;
+ struct watch *watch = NULL;
+ struct mount *m;
+ struct path path;
+ unsigned int lookup_flags =
+ LOOKUP_DIRECTORY | LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
+ int ret;
+
+ if (watch_id < -1 || watch_id > 0xff)
+ return -EINVAL;
+ if ((at_flags & ~(AT_NO_AUTOMOUNT | AT_EMPTY_PATH)) != 0)
+ return -EINVAL;
+ if (at_flags & AT_NO_AUTOMOUNT)
+ lookup_flags &= ~LOOKUP_AUTOMOUNT;
+ if (at_flags & AT_EMPTY_PATH)
+ lookup_flags |= LOOKUP_EMPTY;
+
+ ret = user_path_at(dfd, filename, lookup_flags, &path);
+ if (ret)
+ return ret;
+
+ ret = inode_permission(path.dentry->d_inode, MAY_EXEC);
+ if (ret)
+ goto err_path;
+
+ wqueue = get_watch_queue(watch_fd);
+ if (IS_ERR(wqueue))
+ goto err_path;
+
+ m = real_mount(path.mnt);
+
+ if (watch_id >= 0) {
+ ret = -ENOMEM;
+ if (!READ_ONCE(m->mnt_watchers)) {
+ wlist = kzalloc(sizeof(*wlist), GFP_KERNEL);
+ if (!wlist)
+ goto err_wqueue;
+ init_watch_list(wlist, release_mount_watch);
+ }
+
+ watch = kzalloc(sizeof(*watch), GFP_KERNEL);
+ if (!watch)
+ goto err_wlist;
+
+ init_watch(watch, wqueue);
+ watch->id = (unsigned long)path.dentry;
+ watch->info_id = (u32)watch_id << 24;
+
+ ret = security_watch_mount(watch, &path);
+ if (ret < 0)
+ goto err_watch;
+
+ down_write(&m->mnt.mnt_sb->s_umount);
+ if (!m->mnt_watchers) {
+ m->mnt_watchers = wlist;
+ wlist = NULL;
+ }
+
+ ret = add_watch_to_object(watch, m->mnt_watchers);
+ if (ret == 0) {
+ spin_lock(&path.dentry->d_lock);
+ path.dentry->d_flags |= DCACHE_MOUNT_WATCH;
+ spin_unlock(&path.dentry->d_lock);
+ dget(path.dentry);
+ watch = NULL;
+ }
+ up_write(&m->mnt.mnt_sb->s_umount);
+ } else {
+ down_write(&m->mnt.mnt_sb->s_umount);
+ ret = remove_watch_from_object(m->mnt_watchers, wqueue,
+ (unsigned long)path.dentry,
+ false);
+ up_write(&m->mnt.mnt_sb->s_umount);
+ }
+
+err_watch:
+ kfree(watch);
+err_wlist:
+ kfree(wlist);
+err_wqueue:
+ put_watch_queue(wqueue);
+err_path:
+ path_put(&path);
+ return ret;
+}
diff --git a/fs/namespace.c b/fs/namespace.c
index 85b5f7bea82e..54d237251941 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -498,6 +498,9 @@ static int mnt_make_readonly(struct mount *mnt)
smp_wmb();
mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD;
unlock_mount_hash();
+ if (ret == 0)
+ notify_mount(mnt, NULL, NOTIFY_MOUNT_READONLY,
+ NOTIFY_MOUNT_IS_NOW_RO);
return ret;
}
@@ -506,6 +509,7 @@ static int __mnt_unmake_readonly(struct mount *mnt)
lock_mount_hash();
mnt->mnt.mnt_flags &= ~MNT_READONLY;
unlock_mount_hash();
+ notify_mount(mnt, NULL, NOTIFY_MOUNT_READONLY, 0);
return 0;
}
@@ -819,6 +823,7 @@ static struct mountpoint *unhash_mnt(struct mount *mnt)
*/
static void umount_mnt(struct mount *mnt)
{
+ notify_mount(mnt->mnt_parent, mnt, NOTIFY_MOUNT_UNMOUNT, 0);
put_mountpoint(unhash_mnt(mnt));
}
@@ -1159,6 +1164,11 @@ static void mntput_no_expire(struct mount *mnt)
mnt->mnt.mnt_flags |= MNT_DOOMED;
rcu_read_unlock();
+#ifdef CONFIG_MOUNT_NOTIFICATIONS
+ if (mnt->mnt_watchers)
+ remove_watch_list(mnt->mnt_watchers, mnt->mnt_id);
+#endif
+
list_del(&mnt->mnt_instance);
if (unlikely(!list_empty(&mnt->mnt_mounts))) {
@@ -1453,6 +1463,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
p = list_first_entry(&tmp_list, struct mount, mnt_list);
list_del_init(&p->mnt_expire);
list_del_init(&p->mnt_list);
+
ns = p->mnt_ns;
if (ns) {
ns->mounts--;
@@ -2079,7 +2090,10 @@ static int attach_recursive_mnt(struct mount *source_mnt,
}
if (moving) {
unhash_mnt(source_mnt);
+ notify_mount(source_mnt->mnt_parent, source_mnt,
+ NOTIFY_MOUNT_MOVE_FROM, 0);
attach_mnt(source_mnt, dest_mnt, dest_mp);
+ notify_mount(dest_mnt, source_mnt, NOTIFY_MOUNT_MOVE_TO, 0);
touch_mnt_namespace(source_mnt->mnt_ns);
} else {
if (source_mnt->mnt_ns) {
@@ -2088,6 +2102,11 @@ static int attach_recursive_mnt(struct mount *source_mnt,
}
mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
commit_tree(source_mnt);
+ notify_mount(dest_mnt, source_mnt, NOTIFY_MOUNT_NEW_MOUNT,
+ (source_mnt->mnt.mnt_sb->s_flags & SB_RDONLY ?
+ NOTIFY_MOUNT_IS_NOW_RO : 0) |
+ (source_mnt->mnt.mnt_sb->s_flags & SB_SUBMOUNT ?
+ NOTIFY_MOUNT_IS_SUBMOUNT : 0));
}
hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
@@ -2464,6 +2483,8 @@ static void set_mount_attributes(struct mount *mnt, unsigned int mnt_flags)
mnt->mnt.mnt_flags = mnt_flags;
touch_mnt_namespace(mnt->mnt_ns);
unlock_mount_hash();
+ notify_mount(mnt, NULL, NOTIFY_MOUNT_SETATTR,
+ (mnt_flags & SB_RDONLY ? NOTIFY_MOUNT_IS_NOW_RO : 0));
}
static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *mnt)
@@ -2899,6 +2920,7 @@ void mark_mounts_for_expiry(struct list_head *mounts)
propagate_mount_busy(mnt, 1))
continue;
list_move(&mnt->mnt_expire, &graveyard);
+ notify_mount(mnt, NULL, NOTIFY_MOUNT_EXPIRY, 0);
}
while (!list_empty(&graveyard)) {
mnt = list_first_entry(&graveyard, struct mount, mnt_expire);
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index c1488cc84fd9..7b194d778155 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -217,6 +217,7 @@ struct dentry_operations {
#define DCACHE_PAR_LOOKUP 0x10000000 /* being looked up (with parent locked shared) */
#define DCACHE_DENTRY_CURSOR 0x20000000
#define DCACHE_NORCU 0x40000000 /* No RCU delay for freeing */
+#define DCACHE_MOUNT_WATCH 0x80000000 /* There's a mount watch here */
extern seqlock_t rename_lock;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 1815065d52f3..1fd43af3b22d 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1003,6 +1003,8 @@ asmlinkage long sys_pidfd_send_signal(int pidfd, int sig,
siginfo_t __user *info,
unsigned int flags);
asmlinkage long sys_pidfd_getfd(int pidfd, int fd, unsigned int flags);
+asmlinkage long sys_watch_mount(int dfd, const char __user *path,
+ unsigned int at_flags, int watch_fd, int watch_id);
/*
* Architecture-specific system calls
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 3a3201e4618e..6b5748287883 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -855,9 +855,11 @@ __SYSCALL(__NR_clone3, sys_clone3)
__SYSCALL(__NR_openat2, sys_openat2)
#define __NR_pidfd_getfd 438
__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
+#define __NR_watch_mount 439
+__SYSCALL(__NR_watch_mount, sys_watch_mount)
#undef __NR_syscalls
-#define __NR_syscalls 439
+#define __NR_syscalls 440
/*
* 32 bit systems traditionally used different
diff --git a/include/uapi/linux/watch_queue.h b/include/uapi/linux/watch_queue.h
index c3d8320b5d3a..b0f35cf51394 100644
--- a/include/uapi/linux/watch_queue.h
+++ b/include/uapi/linux/watch_queue.h
@@ -14,7 +14,8 @@
enum watch_notification_type {
WATCH_TYPE_META = 0, /* Special record */
WATCH_TYPE_KEY_NOTIFY = 1, /* Key change event notification */
- WATCH_TYPE__NR = 2
+ WATCH_TYPE_MOUNT_NOTIFY = 2, /* Mount topology change notification */
+ WATCH_TYPE___NR = 3
};
enum watch_meta_notification_subtype {
@@ -101,4 +102,33 @@ struct key_notification {
__u32 aux; /* Per-type auxiliary data */
};
+/*
+ * Type of mount topology change notification.
+ */
+enum mount_notification_subtype {
+ NOTIFY_MOUNT_NEW_MOUNT = 0, /* New mount added */
+ NOTIFY_MOUNT_UNMOUNT = 1, /* Mount removed manually */
+ NOTIFY_MOUNT_EXPIRY = 2, /* Automount expired */
+ NOTIFY_MOUNT_READONLY = 3, /* Mount R/O state changed */
+ NOTIFY_MOUNT_SETATTR = 4, /* Mount attributes changed */
+ NOTIFY_MOUNT_MOVE_FROM = 5, /* Mount moved from here */
+ NOTIFY_MOUNT_MOVE_TO = 6, /* Mount moved to here (compare op_id) */
+};
+
+#define NOTIFY_MOUNT_IN_SUBTREE WATCH_INFO_FLAG_0 /* Event not actually at watched dentry */
+#define NOTIFY_MOUNT_IS_RECURSIVE WATCH_INFO_FLAG_1 /* Change applied recursively */
+#define NOTIFY_MOUNT_IS_NOW_RO WATCH_INFO_FLAG_2 /* Mount changed to R/O */
+#define NOTIFY_MOUNT_IS_SUBMOUNT WATCH_INFO_FLAG_3 /* New mount is submount */
+
+/*
+ * Mount topology/configuration change notification record.
+ * - watch.type = WATCH_TYPE_MOUNT_NOTIFY
+ * - watch.subtype = enum mount_notification_subtype
+ */
+struct mount_notification {
+ struct watch_notification watch; /* WATCH_TYPE_MOUNT_NOTIFY */
+ __u32 triggered_on; /* The mount that the notify was on */
+ __u32 changed_mount; /* The mount that got changed */
+};
+
#endif /* _UAPI_LINUX_WATCH_QUEUE_H */
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 3b69a560a7ac..3e1c5c9d2efe 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -85,6 +85,9 @@ COND_SYSCALL(ioprio_get);
/* fs/locks.c */
COND_SYSCALL(flock);
+/* fs/mount_notify.c */
+COND_SYSCALL(watch_mount);
+
/* fs/namei.c */
/* fs/namespace.c */
^ permalink raw reply related
* [RFC PATCH 14/17] watch_queue: sample: Display mount tree change notifications [ver #4]
From: David Howells @ 2020-03-09 12:19 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, dhowells, casey, sds, nicolas.dichtel, raven, christian,
andres, jlayton, dray, kzak, keyrings, linux-api, linux-fsdevel,
linux-security-module, linux-kernel
In-Reply-To: <158375623086.334846.16121725232323108842.stgit@warthog.procyon.org.uk>
This is run like:
./watch_test
and watches "/" for changes to the mount topology and the attributes of
individual mount objects.
# mount -t tmpfs none /mnt
# mount -o remount,ro /mnt
# mount -o remount,rw /mnt
producing:
# ./watch_test
read() = 16
NOTIFY[000]: ty=000002 sy=00 i=02000010
MOUNT 00000060 change=0[new_mount] aux=416
read() = 16
NOTIFY[000]: ty=000002 sy=04 i=02010010
MOUNT 000001a0 change=4[setattr] aux=0
read() = 16
NOTIFY[000]: ty=000002 sy=04 i=02010010
MOUNT 000001a0 change=4[setattr] aux=0
Signed-off-by: David Howells <dhowells@redhat.com>
---
samples/watch_queue/watch_test.c | 39 +++++++++++++++++++++++++++++++++++++-
1 file changed, 38 insertions(+), 1 deletion(-)
diff --git a/samples/watch_queue/watch_test.c b/samples/watch_queue/watch_test.c
index 0eaff5dc04c3..49d185150506 100644
--- a/samples/watch_queue/watch_test.c
+++ b/samples/watch_queue/watch_test.c
@@ -26,6 +26,9 @@
#ifndef __NR_watch_devices
#define __NR_watch_devices -1
#endif
+#ifndef __NR_watch_mount
+#define __NR_watch_mount -1
+#endif
#define BUF_SIZE 256
@@ -58,6 +61,27 @@ static void saw_key_change(struct watch_notification *n, size_t len)
k->key_id, n->subtype, key_subtypes[n->subtype], k->aux);
}
+static const char *mount_subtypes[256] = {
+ [NOTIFY_MOUNT_NEW_MOUNT] = "new_mount",
+ [NOTIFY_MOUNT_UNMOUNT] = "unmount",
+ [NOTIFY_MOUNT_EXPIRY] = "expiry",
+ [NOTIFY_MOUNT_READONLY] = "readonly",
+ [NOTIFY_MOUNT_SETATTR] = "setattr",
+ [NOTIFY_MOUNT_MOVE_FROM] = "move_from",
+ [NOTIFY_MOUNT_MOVE_TO] = "move_to",
+};
+
+static void saw_mount_change(struct watch_notification *n, size_t len)
+{
+ struct mount_notification *m = (struct mount_notification *)n;
+
+ if (len != sizeof(struct mount_notification))
+ return;
+
+ printf("MOUNT %08x change=%u[%s] aux=%u\n",
+ m->triggered_on, n->subtype, mount_subtypes[n->subtype], m->changed_mount);
+}
+
/*
* Consume and display events.
*/
@@ -134,6 +158,9 @@ static void consumer(int fd)
default:
printf("other type\n");
break;
+ case WATCH_TYPE_MOUNT_NOTIFY:
+ saw_mount_change(&n.n, len);
+ break;
}
p += len;
@@ -142,12 +169,17 @@ static void consumer(int fd)
}
static struct watch_notification_filter filter = {
- .nr_filters = 1,
+ .nr_filters = 2,
.filters = {
[0] = {
.type = WATCH_TYPE_KEY_NOTIFY,
.subtype_filter[0] = UINT_MAX,
},
+ [1] = {
+ .type = WATCH_TYPE_MOUNT_NOTIFY,
+ // Reject move-from notifications
+ .subtype_filter[0] = UINT_MAX & ~(1 << NOTIFY_MOUNT_MOVE_FROM),
+ },
},
};
@@ -181,6 +213,11 @@ int main(int argc, char **argv)
exit(1);
}
+ if (syscall(__NR_watch_mount, AT_FDCWD, "/", 0, fd, 0x02) == -1) {
+ perror("watch_mount");
+ exit(1);
+ }
+
consumer(fd);
exit(0);
}
^ permalink raw reply related
* [RFC PATCH 15/17] watch_queue: Introduce a non-repeating system-unique superblock ID [ver #4]
From: David Howells @ 2020-03-09 12:19 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, dhowells, casey, sds, nicolas.dichtel, raven, christian,
andres, jlayton, dray, kzak, keyrings, linux-api, linux-fsdevel,
linux-security-module, linux-kernel
In-Reply-To: <158375623086.334846.16121725232323108842.stgit@warthog.procyon.org.uk>
Introduce an (effectively) non-repeating system-unique superblock ID that
can be used to determine that two object are in the same superblock without
risking reuse of the ID in the meantime (as is possible with device IDs).
The ID is time-based to make it harder to use it as a covert communications
channel.
In future patches, this ID will be used to tag superblock notification
messages. It will also be made queryable.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/internal.h | 1 +
fs/super.c | 24 ++++++++++++++++++++++++
include/linux/fs.h | 3 +++
3 files changed, 28 insertions(+)
diff --git a/fs/internal.h b/fs/internal.h
index f3f280b952a3..a0d90f23593c 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -109,6 +109,7 @@ extern int reconfigure_super(struct fs_context *);
extern bool trylock_super(struct super_block *sb);
extern struct super_block *user_get_super(dev_t);
extern bool mount_capable(struct fs_context *);
+extern void vfs_generate_unique_id(u64 *);
/*
* open.c
diff --git a/fs/super.c b/fs/super.c
index cd352530eca9..ececa5695fd1 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -44,6 +44,8 @@ static int thaw_super_locked(struct super_block *sb);
static LIST_HEAD(super_blocks);
static DEFINE_SPINLOCK(sb_lock);
+static u64 vfs_last_identifier;
+static u64 vfs_identifier_offset;
static char *sb_writers_name[SB_FREEZE_LEVELS] = {
"sb_writers",
@@ -273,6 +275,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags,
goto fail;
if (list_lru_init_memcg(&s->s_inode_lru, &s->s_shrink))
goto fail;
+ vfs_generate_unique_id(&s->s_unique_id);
return s;
fail:
@@ -1867,3 +1870,24 @@ int thaw_super(struct super_block *sb)
return thaw_super_locked(sb);
}
EXPORT_SYMBOL(thaw_super);
+
+/*
+ * Generate a unique identifier for a superblock or mount object.
+ */
+void vfs_generate_unique_id(u64 *_id)
+{
+ u64 id = ktime_to_ns(ktime_get());
+
+ spin_lock(&sb_lock);
+
+ id += vfs_identifier_offset;
+ if (id <= vfs_last_identifier) {
+ id = vfs_last_identifier + 1;
+ vfs_identifier_offset = vfs_last_identifier - id;
+ }
+
+ vfs_last_identifier = id;
+ spin_unlock(&sb_lock);
+
+ *_id = id;
+}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3cd4fe6b845e..9de6bfe41016 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1548,6 +1548,9 @@ struct super_block {
spinlock_t s_inode_wblist_lock;
struct list_head s_inodes_wb; /* writeback inodes */
+
+ /* Superblock event notifications */
+ u64 s_unique_id;
} __randomize_layout;
/* Helper functions so that in most cases filesystems will
^ permalink raw reply related
* [RFC PATCH 16/17] watch_queue: Add superblock notifications [ver #4]
From: David Howells @ 2020-03-09 12:19 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, dhowells, casey, sds, nicolas.dichtel, raven, christian,
andres, jlayton, dray, kzak, keyrings, linux-api, linux-fsdevel,
linux-security-module, linux-kernel
In-Reply-To: <158375623086.334846.16121725232323108842.stgit@warthog.procyon.org.uk>
Add a superblock event notification facility whereby notifications about
superblock events, such as I/O errors (EIO), quota limits being hit
(EDQUOT) and running out of space (ENOSPC) can be reported to a monitoring
process asynchronously. Note that this does not cover vfsmount topology
changes. watch_mount() is used for that.
Firstly, a watch queue needs to be created:
pipe2(fds, O_NOTIFICATION_PIPE);
ioctl(fds[1], IOC_WATCH_QUEUE_SET_SIZE, 256);
then a notification can be set up to report notifications via that queue:
struct watch_notification_filter filter = {
.nr_filters = 1,
.filters = {
[0] = {
.type = WATCH_TYPE_SB_NOTIFY,
.subtype_filter[0] = UINT_MAX,
},
},
};
ioctl(fds[1], IOC_WATCH_QUEUE_SET_FILTER, &filter);
watch_sb(AT_FDCWD, "/home/dhowells", 0, fds[1], 0x03);
In this case, it would let me monitor my own homedir for events. After
setting the watch, records will be placed into the queue when, for example,
as superblock switches between read-write and read-only. Records are of
the following format:
struct superblock_notification {
struct watch_notification watch;
__u64 sb_id;
} *n;
Where:
n->watch.type will be WATCH_TYPE_SB_NOTIFY.
n->watch.subtype will indicate the type of event, such as
NOTIFY_SUPERBLOCK_READONLY.
n->watch.info & WATCH_INFO_LENGTH will indicate the length of the
record.
n->watch.info & WATCH_INFO_ID will be the fifth argument to
watch_sb(), shifted.
n->watch.info & NOTIFY_SUPERBLOCK_IS_NOW_RO will be used for
NOTIFY_SUPERBLOCK_READONLY, being set if the superblock becomes
R/O, and being cleared otherwise.
n->sb_id will be the ID of the superblock, as can be retrieved with
the fsinfo() syscall, as part of the fsinfo_sb_notifications
attribute in the the watch_id field.
Note that it is permissible for event records to be of variable length -
or, at least, the length may be dependent on the subtype. Note also that
the queue can be shared between multiple notifications of various types.
Signed-off-by: David Howells <dhowells@redhat.com>
---
arch/alpha/kernel/syscalls/syscall.tbl | 1
arch/arm/tools/syscall.tbl | 1
arch/arm64/include/asm/unistd.h | 2
arch/ia64/kernel/syscalls/syscall.tbl | 1
arch/m68k/kernel/syscalls/syscall.tbl | 1
arch/microblaze/kernel/syscalls/syscall.tbl | 1
arch/mips/kernel/syscalls/syscall_n32.tbl | 1
arch/mips/kernel/syscalls/syscall_n64.tbl | 1
arch/mips/kernel/syscalls/syscall_o32.tbl | 1
arch/parisc/kernel/syscalls/syscall.tbl | 1
arch/powerpc/kernel/syscalls/syscall.tbl | 1
arch/s390/kernel/syscalls/syscall.tbl | 1
arch/sh/kernel/syscalls/syscall.tbl | 1
arch/sparc/kernel/syscalls/syscall.tbl | 1
arch/x86/entry/syscalls/syscall_32.tbl | 1
arch/x86/entry/syscalls/syscall_64.tbl | 1
arch/xtensa/kernel/syscalls/syscall.tbl | 1
fs/Kconfig | 12 ++
fs/super.c | 132 +++++++++++++++++++++++++++
include/linux/fs.h | 81 +++++++++++++++++
include/linux/syscalls.h | 2
include/uapi/asm-generic/unistd.h | 4 +
include/uapi/linux/watch_queue.h | 31 ++++++
kernel/sys_ni.c | 3 +
24 files changed, 280 insertions(+), 3 deletions(-)
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index b869428033ef..7c0115af9010 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -478,3 +478,4 @@
547 common openat2 sys_openat2
548 common pidfd_getfd sys_pidfd_getfd
549 common watch_mount sys_watch_mount
+550 common watch_sb sys_watch_sb
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 9c389da9efcc..f256f009a89f 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -452,3 +452,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
+440 common watch_sb sys_watch_sb
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 75f04a1023be..bc0f923e0e04 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -38,7 +38,7 @@
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5)
#define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 440
+#define __NR_compat_syscalls 441
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index 6817f865cc71..a4dafc659647 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -359,3 +359,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
+440 common watch_sb sys_watch_sb
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index fbf85da75ecb..893fb4151547 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -438,3 +438,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
+440 common watch_sb sys_watch_sb
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index b05b192da1e2..54aaf0d40c64 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -444,3 +444,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
+440 common watch_sb sys_watch_sb
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 0f85d2a033f9..fd34dd0efed0 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -377,3 +377,4 @@
437 n32 openat2 sys_openat2
438 n32 pidfd_getfd sys_pidfd_getfd
439 n32 watch_mount sys_watch_mount
+440 n32 watch_sb sys_watch_sb
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 905cf9ac0792..db0f4c0a0a0b 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -353,3 +353,4 @@
437 n64 openat2 sys_openat2
438 n64 pidfd_getfd sys_pidfd_getfd
439 n64 watch_mount sys_watch_mount
+440 n64 watch_sb sys_watch_sb
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 834b26b08d74..ce2e1326de8f 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -426,3 +426,4 @@
437 o32 openat2 sys_openat2
438 o32 pidfd_getfd sys_pidfd_getfd
439 o32 watch_mount sys_watch_mount
+440 o32 watch_sb sys_watch_sb
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index badd3449db43..6e4a7c08b64b 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -436,3 +436,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
+440 common watch_sb sys_watch_sb
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index b404361bc929..08943f3b8206 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -520,3 +520,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
+440 common watch_sb sys_watch_sb
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 33071de24511..b3b8529d2b74 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -441,3 +441,4 @@
437 common openat2 sys_openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount sys_watch_mount
+440 common watch_sb sys_watch_sb sys_watch_sb
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 682c125122f4..89307a20657c 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -441,3 +441,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
+440 common watch_sb sys_watch_sb
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index febf3cd675e3..4ff841a00450 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -484,3 +484,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
+440 common watch_sb sys_watch_sb
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 085bcc5afdf1..e2731d295f88 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -443,3 +443,4 @@
437 i386 openat2 sys_openat2 __ia32_sys_openat2
438 i386 pidfd_getfd sys_pidfd_getfd __ia32_sys_pidfd_getfd
439 i386 watch_mount sys_watch_mount __ia32_sys_watch_mount
+440 i386 watch_sb sys_watch_sb __ia32_sys_watch_sb
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 9cfb6b2eb319..f4391176102c 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -360,6 +360,7 @@
437 common openat2 __x64_sys_openat2
438 common pidfd_getfd __x64_sys_pidfd_getfd
439 common watch_mount __x64_sys_watch_mount
+440 common watch_sb __x64_sys_watch_sb
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 1a066a43a58b..8e7d731ed6cf 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -409,3 +409,4 @@
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
+440 common watch_sb sys_watch_sb
diff --git a/fs/Kconfig b/fs/Kconfig
index d7039137d538..fef1365c23a5 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -126,6 +126,18 @@ config MOUNT_NOTIFICATIONS
device to handle the notification buffer and provides the
mount_notify() system call to enable/disable watchpoints.
+config SB_NOTIFICATIONS
+ bool "Superblock event notifications"
+ select WATCH_QUEUE
+ help
+ This option provides support for receiving superblock event
+ notifications. This makes use of the /dev/watch_queue misc device to
+ handle the notification buffer and provides the sb_notify() system
+ call to enable/disable watches.
+
+ Events can include things like changing between R/W and R/O, EIO
+ generation, ENOSPC generation and EDQUOT generation.
+
source "fs/quota/Kconfig"
source "fs/autofs/Kconfig"
diff --git a/fs/super.c b/fs/super.c
index ececa5695fd1..a7aa16ca380c 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -37,6 +37,8 @@
#include <linux/lockdep.h>
#include <linux/user_namespace.h>
#include <linux/fs_context.h>
+#include <linux/syscalls.h>
+#include <linux/namei.h>
#include <uapi/linux/mount.h>
#include "internal.h"
@@ -333,6 +335,10 @@ void deactivate_locked_super(struct super_block *s)
{
struct file_system_type *fs = s->s_type;
if (atomic_dec_and_test(&s->s_active)) {
+#ifdef CONFIG_SB_NOTIFICATIONS
+ if (s->s_watchers)
+ remove_watch_list(s->s_watchers, s->s_unique_id);
+#endif
cleancache_invalidate_fs(s);
unregister_shrinker(&s->s_shrink);
fs->kill_sb(s);
@@ -972,6 +978,8 @@ int reconfigure_super(struct fs_context *fc)
/* Needs to be ordered wrt mnt_is_readonly() */
smp_wmb();
sb->s_readonly_remount = 0;
+ notify_sb(sb, NOTIFY_SUPERBLOCK_READONLY,
+ remount_ro ? NOTIFY_SUPERBLOCK_IS_NOW_RO : 0);
/*
* Some filesystems modify their metadata via some other path than the
@@ -1891,3 +1899,127 @@ void vfs_generate_unique_id(u64 *_id)
*_id = id;
}
+
+#ifdef CONFIG_SB_NOTIFICATIONS
+/*
+ * Post superblock notifications.
+ */
+void post_sb_notification(struct super_block *s, struct superblock_notification *n)
+{
+ post_watch_notification(s->s_watchers, &n->watch, current_cred(),
+ s->s_unique_id);
+}
+
+static void sb_release_watch(struct watch *watch)
+{
+ put_super(watch->private);
+}
+
+/**
+ * sys_watch_sb - Watch for superblock events.
+ * @dfd: Base directory to pathwalk from or fd referring to superblock.
+ * @filename: Path to superblock to place the watch upon
+ * @at_flags: Pathwalk control flags
+ * @watch_fd: The watch queue to send notifications to.
+ * @watch_id: The watch ID to be placed in the notification (-1 to remove watch)
+ */
+SYSCALL_DEFINE5(watch_sb,
+ int, dfd,
+ const char __user *, filename,
+ unsigned int, at_flags,
+ int, watch_fd,
+ int, watch_id)
+{
+ struct watch_queue *wqueue;
+ struct super_block *s;
+ struct watch_list *wlist = NULL;
+ struct watch *watch = NULL;
+ struct path path;
+ unsigned int lookup_flags =
+ LOOKUP_DIRECTORY | LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
+ bool drop_s_count = false;
+ int ret;
+
+ if (watch_id < -1 || watch_id > 0xff)
+ return -EINVAL;
+ if ((at_flags & ~(AT_NO_AUTOMOUNT | AT_EMPTY_PATH)) != 0)
+ return -EINVAL;
+ if (at_flags & AT_NO_AUTOMOUNT)
+ lookup_flags &= ~LOOKUP_AUTOMOUNT;
+ if (at_flags & AT_EMPTY_PATH)
+ lookup_flags |= LOOKUP_EMPTY;
+
+ ret = user_path_at(dfd, filename, at_flags, &path);
+ if (ret)
+ return ret;
+
+ ret = inode_permission(path.dentry->d_inode, MAY_EXEC);
+ if (ret)
+ goto err_path;
+
+ wqueue = get_watch_queue(watch_fd);
+ if (IS_ERR(wqueue))
+ goto err_path;
+
+ s = path.dentry->d_sb;
+ if (watch_id >= 0) {
+ ret = -ENOMEM;
+ if (!READ_ONCE(s->s_watchers)) {
+ wlist = kzalloc(sizeof(*wlist), GFP_KERNEL);
+ if (!wlist)
+ goto err_wqueue;
+ init_watch_list(wlist, sb_release_watch);
+ }
+
+ watch = kzalloc(sizeof(*watch), GFP_KERNEL);
+ if (!watch)
+ goto err_wlist;
+
+ init_watch(watch, wqueue);
+ watch->id = s->s_unique_id;
+ watch->private = s;
+ watch->info_id = (u32)watch_id << 24;
+
+ ret = security_watch_sb(watch, s);
+ if (ret < 0)
+ goto err_watch;
+
+ down_write(&s->s_umount);
+ ret = -EIO;
+ if (atomic_read(&s->s_active)) {
+ if (!s->s_watchers) {
+ s->s_watchers = wlist;
+ wlist = NULL;
+ }
+
+ spin_lock(&sb_lock);
+ s->s_count++;
+ spin_unlock(&sb_lock);
+ ret = add_watch_to_object(watch, s->s_watchers);
+ if (ret == 0)
+ watch = NULL; /* It worked */
+ else
+ drop_s_count = true;
+ }
+ up_write(&s->s_umount);
+ if (drop_s_count)
+ put_super(s);
+ } else {
+ ret = -EBADSLT;
+ down_write(&s->s_umount);
+ ret = remove_watch_from_object(s->s_watchers, wqueue,
+ s->s_unique_id, false);
+ up_write(&s->s_umount);
+ }
+
+err_watch:
+ kfree(watch);
+err_wlist:
+ kfree(wlist);
+err_wqueue:
+ put_watch_queue(wqueue);
+err_path:
+ path_put(&path);
+ return ret;
+}
+#endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9de6bfe41016..9181cfcd5265 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -40,6 +40,7 @@
#include <linux/fs_types.h>
#include <linux/build_bug.h>
#include <linux/stddef.h>
+#include <linux/watch_queue.h>
#include <asm/byteorder.h>
#include <uapi/linux/fs.h>
@@ -1551,6 +1552,12 @@ struct super_block {
/* Superblock event notifications */
u64 s_unique_id;
+
+#ifdef CONFIG_SB_NOTIFICATIONS
+ struct watch_list *s_watchers;
+#endif
+ atomic_t s_change_counter; /* Count of config change notifications */
+ atomic_t s_notify_counter; /* Count of other notifications */
} __randomize_layout;
/* Helper functions so that in most cases filesystems will
@@ -3654,4 +3661,78 @@ static inline int inode_drain_writes(struct inode *inode)
return filemap_write_and_wait(inode->i_mapping);
}
+extern void post_sb_notification(struct super_block *, struct superblock_notification *);
+
+/**
+ * notify_sb: Post simple superblock notification.
+ * @s: The superblock the notification is about.
+ * @subtype: The type of notification.
+ * @info: WATCH_INFO_FLAG_* flags to be set in the record.
+ */
+static inline void notify_sb(struct super_block *s,
+ enum superblock_notification_type subtype,
+ u32 info)
+{
+#ifdef CONFIG_SB_NOTIFICATIONS
+ atomic_inc(&s->s_change_counter);
+ if (unlikely(READ_ONCE(s->s_watchers))) {
+ struct superblock_notification n = {
+ .watch.type = WATCH_TYPE_SB_NOTIFY,
+ .watch.subtype = subtype,
+ .watch.info = watch_sizeof(n) | info,
+ .sb_id = s->s_unique_id,
+ };
+
+ post_sb_notification(s, &n);
+ }
+#endif
+}
+
+/**
+ * notify_sb_error: Post superblock error notification.
+ * @s: The superblock the notification is about.
+ * @error: The error number to be recorded.
+ */
+static inline int notify_sb_error(struct super_block *s, int error)
+{
+#ifdef CONFIG_SB_NOTIFICATIONS
+ atomic_inc(&s->s_notify_counter);
+ if (unlikely(READ_ONCE(s->s_watchers))) {
+ struct superblock_error_notification n = {
+ .s.watch.type = WATCH_TYPE_SB_NOTIFY,
+ .s.watch.subtype = NOTIFY_SUPERBLOCK_ERROR,
+ .s.watch.info = watch_sizeof(n),
+ .s.sb_id = s->s_unique_id,
+ .error_number = error,
+ .error_cookie = 0,
+ };
+
+ post_sb_notification(s, &n.s);
+ }
+#endif
+ return error;
+}
+
+/**
+ * notify_sb_EDQUOT: Post superblock quota overrun notification.
+ * @s: The superblock the notification is about.
+ */
+static inline int notify_sb_EQDUOT(struct super_block *s)
+{
+#ifdef CONFIG_SB_NOTIFICATIONS
+ atomic_inc(&s->s_notify_counter);
+ if (unlikely(READ_ONCE(s->s_watchers))) {
+ struct superblock_notification n = {
+ .watch.type = WATCH_TYPE_SB_NOTIFY,
+ .watch.subtype = NOTIFY_SUPERBLOCK_EDQUOT,
+ .watch.info = watch_sizeof(n),
+ .sb_id = s->s_unique_id,
+ };
+
+ post_sb_notification(s, &n);
+ }
+#endif
+ return -EDQUOT;
+}
+
#endif /* _LINUX_FS_H */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 1fd43af3b22d..c84440d57f52 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1005,6 +1005,8 @@ asmlinkage long sys_pidfd_send_signal(int pidfd, int sig,
asmlinkage long sys_pidfd_getfd(int pidfd, int fd, unsigned int flags);
asmlinkage long sys_watch_mount(int dfd, const char __user *path,
unsigned int at_flags, int watch_fd, int watch_id);
+asmlinkage long sys_watch_sb(int dfd, const char __user *path,
+ unsigned int at_flags, int watch_fd, int watch_id);
/*
* Architecture-specific system calls
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 6b5748287883..5bff318b7ffa 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -857,9 +857,11 @@ __SYSCALL(__NR_openat2, sys_openat2)
__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
#define __NR_watch_mount 439
__SYSCALL(__NR_watch_mount, sys_watch_mount)
+#define __NR_watch_sb 440
+__SYSCALL(__NR_watch_sb, sys_watch_sb)
#undef __NR_syscalls
-#define __NR_syscalls 440
+#define __NR_syscalls 441
/*
* 32 bit systems traditionally used different
diff --git a/include/uapi/linux/watch_queue.h b/include/uapi/linux/watch_queue.h
index b0f35cf51394..e9c37b1ae68d 100644
--- a/include/uapi/linux/watch_queue.h
+++ b/include/uapi/linux/watch_queue.h
@@ -15,7 +15,8 @@ enum watch_notification_type {
WATCH_TYPE_META = 0, /* Special record */
WATCH_TYPE_KEY_NOTIFY = 1, /* Key change event notification */
WATCH_TYPE_MOUNT_NOTIFY = 2, /* Mount topology change notification */
- WATCH_TYPE___NR = 3
+ WATCH_TYPE_SB_NOTIFY = 3, /* Superblock event notification */
+ WATCH_TYPE___NR = 4
};
enum watch_meta_notification_subtype {
@@ -131,4 +132,32 @@ struct mount_notification {
__u32 changed_mount; /* The mount that got changed */
};
+/*
+ * Type of superblock notification.
+ */
+enum superblock_notification_type {
+ NOTIFY_SUPERBLOCK_READONLY = 0, /* Filesystem toggled between R/O and R/W */
+ NOTIFY_SUPERBLOCK_ERROR = 1, /* Error in filesystem or blockdev */
+ NOTIFY_SUPERBLOCK_EDQUOT = 2, /* EDQUOT notification */
+ NOTIFY_SUPERBLOCK_NETWORK = 3, /* Network status change */
+};
+
+#define NOTIFY_SUPERBLOCK_IS_NOW_RO WATCH_INFO_FLAG_0 /* Superblock changed to R/O */
+
+/*
+ * Superblock notification record.
+ * - watch.type = WATCH_TYPE_MOUNT_NOTIFY
+ * - watch.subtype = enum superblock_notification_subtype
+ */
+struct superblock_notification {
+ struct watch_notification watch; /* WATCH_TYPE_SB_NOTIFY */
+ __u64 sb_id; /* 64-bit superblock ID */
+};
+
+struct superblock_error_notification {
+ struct superblock_notification s; /* subtype = notify_superblock_error */
+ __u32 error_number;
+ __u32 error_cookie;
+};
+
#endif /* _UAPI_LINUX_WATCH_QUEUE_H */
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 3e1c5c9d2efe..0ce01f86e5db 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -119,6 +119,9 @@ COND_SYSCALL_COMPAT(signalfd4);
/* fs/sync.c */
+/* fs/super.c */
+COND_SYSCALL(watch_sb);
+
/* fs/timerfd.c */
COND_SYSCALL(timerfd_create);
COND_SYSCALL(timerfd_settime);
^ permalink raw reply related
* [RFC PATCH 17/17] watch_queue: sample: Display superblock notifications [ver #4]
From: David Howells @ 2020-03-09 12:19 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, dhowells, casey, sds, nicolas.dichtel, raven, christian,
andres, jlayton, dray, kzak, keyrings, linux-api, linux-fsdevel,
linux-security-module, linux-kernel
In-Reply-To: <158375623086.334846.16121725232323108842.stgit@warthog.procyon.org.uk>
The notification is run as:
./watch_test
and it then watches "/mnt" for superblock notifications:
# mount -t tmpfs none /mnt
# ./watch_test &
# mount -o remount,ro /mnt
# mount -o remount,rw /mnt
producing:
# ./watch_test
NOTIFY[000]: ty=000003 sy=00 i=03010010
SUPER 157eb57ca7 change=0[readonly]
read() = 16
NOTIFY[000]: ty=000002 sy=04 i=02010010
MOUNT 000001a0 change=4[setattr] aux=0
read() = 16
NOTIFY[000]: ty=000002 sy=04 i=02010010
MOUNT 000001a0 change=4[setattr] aux=0
Signed-off-by: David Howells <dhowells@redhat.com>
---
samples/watch_queue/watch_test.c | 39 +++++++++++++++++++++++++++++++++++++-
1 file changed, 38 insertions(+), 1 deletion(-)
diff --git a/samples/watch_queue/watch_test.c b/samples/watch_queue/watch_test.c
index 49d185150506..eea3bd8c6569 100644
--- a/samples/watch_queue/watch_test.c
+++ b/samples/watch_queue/watch_test.c
@@ -29,6 +29,9 @@
#ifndef __NR_watch_mount
#define __NR_watch_mount -1
#endif
+#ifndef __NR_watch_sb
+#define __NR_watch_sb -1
+#endif
#define BUF_SIZE 256
@@ -82,6 +85,24 @@ static void saw_mount_change(struct watch_notification *n, size_t len)
m->triggered_on, n->subtype, mount_subtypes[n->subtype], m->changed_mount);
}
+static const char *super_subtypes[256] = {
+ [NOTIFY_SUPERBLOCK_READONLY] = "readonly",
+ [NOTIFY_SUPERBLOCK_ERROR] = "error",
+ [NOTIFY_SUPERBLOCK_EDQUOT] = "edquot",
+ [NOTIFY_SUPERBLOCK_NETWORK] = "network",
+};
+
+static void saw_super_change(struct watch_notification *n, size_t len)
+{
+ struct superblock_notification *s = (struct superblock_notification *)n;
+
+ if (len < sizeof(struct superblock_notification))
+ return;
+
+ printf("SUPER %08llx change=%u[%s]\n",
+ s->sb_id, n->subtype, super_subtypes[n->subtype]);
+}
+
/*
* Consume and display events.
*/
@@ -161,6 +182,9 @@ static void consumer(int fd)
case WATCH_TYPE_MOUNT_NOTIFY:
saw_mount_change(&n.n, len);
break;
+ case WATCH_TYPE_SB_NOTIFY:
+ saw_super_change(&n.n, len);
+ break;
}
p += len;
@@ -169,7 +193,7 @@ static void consumer(int fd)
}
static struct watch_notification_filter filter = {
- .nr_filters = 2,
+ .nr_filters = 3,
.filters = {
[0] = {
.type = WATCH_TYPE_KEY_NOTIFY,
@@ -180,6 +204,14 @@ static struct watch_notification_filter filter = {
// Reject move-from notifications
.subtype_filter[0] = UINT_MAX & ~(1 << NOTIFY_MOUNT_MOVE_FROM),
},
+ [2] = {
+ .type = WATCH_TYPE_SB_NOTIFY,
+ // Only accept notification of changes to R/O state
+ .subtype_filter[0] = (1 << NOTIFY_SUPERBLOCK_READONLY),
+ // Only accept notifications of change-to-R/O
+ .info_mask = WATCH_INFO_FLAG_0,
+ .info_filter = WATCH_INFO_FLAG_0,
+ },
},
};
@@ -218,6 +250,11 @@ int main(int argc, char **argv)
exit(1);
}
+ if (syscall(__NR_watch_sb, AT_FDCWD, "/mnt", 0, fd, 0x03) == -1) {
+ perror("watch_sb");
+ exit(1);
+ }
+
consumer(fd);
exit(0);
}
^ permalink raw reply related
* [PATCH 00/14] VFS: Filesystem information [ver #18]
From: David Howells @ 2020-03-09 14:00 UTC (permalink / raw)
To: torvalds, viro
Cc: Theodore Ts'o, Stefan Metzmacher, Andreas Dilger, linux-ext4,
Aleksa Sarai, Trond Myklebust, Anna Schumaker, linux-nfs,
linux-api, dhowells, raven, mszeredi, christian, jannh,
darrick.wong, kzak, jlayton, linux-api, linux-fsdevel,
linux-security-module, linux-kernel
Here's a set of patches that adds a system call, fsinfo(), that allows
information about the VFS, mount topology, superblock and files to be
retrieved.
The patchset is based on top of the notifications patchset and allows event
counters implemented in the latter to be retrieved to allow overruns to be
efficiently managed.
Included are a couple of sample programs plus limited example code for NFS
and Ext4. The example code is not intended to go upstream as-is.
=======
THE WHY
=======
Why do we want this?
Using /proc/mounts (or similar) has problems:
(1) Reading from it holds a global lock (namespace_sem) that prevents
mounting and unmounting. Lots of data is encoded and mangled into
text whilst the lock is held, including superblock option strings and
mount point paths. This causes performance problems when there are a
lot of mount objects in a system.
(2) Even though namespace_sem is held during a read, reading the whole
file isn't necessarily atomic with respect to mount-type operations.
If a read isn't satisfied in one go, then it may return to userspace
briefly and then continue reading some way into the file. But changes
can occur in the interval that may then go unseen.
(3) Determining what has changed means parsing and comparing consecutive
outputs of /proc/mounts.
(4) Querying a specific mount or superblock means searching through
/proc/mounts and searching by path or mount ID - but we might have an
fd we want to query.
(5) Mount topology is not explicit. One must derive it manually by
comparing entries.
(6) Whilst you can poll() it for events, it only tells you that something
changed in the namespace, not what or whether you can even see the
change.
To fix the notification issues, the preceding notifications patchset added
mount watch notifications whereby you can watch for notifications in a
specific mount subtree. The notification messages include the ID(s) of the
affected mounts.
To support notifications, however, we need to be able to handle overruns in
the notification queue. I added a number of event counters to struct
super_block and struct mount to allow you to pin down the changes, but
there needs to be a way to retrieve them. Exposing them through /proc
would require adding yet another /proc/mounts-type file. We could add
per-mount directories full of attributes in sysfs, but that has issues also
(see below).
Adding an extensible system call interface for retrieving filesystem
information also allows other things to be exposed:
(1) Jeff Layton's error handling changes need a way to allow error event
information to be retrieved.
(2) Bits in masks returned by things like statx() and FS_IOC_GETFLAGS are
actually 3-state { Set, Unset, Not supported }. It could be useful to
provide a way to expose information like this[*].
(3) Limits of the numerical metadata values in a filesystem[*].
(4) Filesystem capability information[*]. Filesystems don't all have the
same capabilities, and even different instances may have different
capabilities, particularly with network filesystems where the set of
may be server-dependent. Capabilities might even vary at file
granularity - though possibly such information should be conveyed
through statx() instead.
(5) ID mapping/shifting tables in use for a superblock.
(6) Filesystem-specific information. I need something for AFS so that I
can do pioctl()-emulation, thereby allowing me to implement certain of
the AFS command line utilities that query state of a particular file.
This could also have application for other filesystems, such as NFS,
CIFS and ext4.
[*] In a lot of cases these are probably fixed and can be memcpy'd from
static data.
There's a further consideration: I want to make it possible to have
fsconfig(fd, FSCONFIG_CMD_CREATE) be intercepted by a container manager
such that the manager can supervise a mount attempted inside the container.
The manager would be given an fd pointing to the fs_context struct and
would then need some way to query it (fsinfo()) and modify it (fsconfig()).
This could also be used to arbitrate user-requested mounts when containers
are not in play.
============================
WHY NOT USE PROCFS OR SYSFS?
============================
Why is it better to go with a new system call rather than adding more magic
stuff to /proc or /sysfs for each superblock object and each mount object?
(1) It can be targetted. It makes it easy to query directly by path or
fd, but can also query by mount ID or fscontext fd. procfs and sysfs
cannot do three of these things easily.
(2) Easier to provide LSM oversight. Is the accessing process allowed to
query information pertinent to a particular file?
(3) It's more efficient as we can return specific binary data rather than
making huge text dumps. Granted, sysfs and procfs could present the
same data, though as lots of little files which have to be
individually opened, read, closed and parsed.
(4) We wouldn't have the overhead of open and close (even adding a
self-contained readfile() syscall has to do that internally).
(5) Opening a file in procfs or sysfs has a pathwalk overhead for each
file accessed. We can use an integer attribute ID instead (yes, this
is similar to ioctl) - but could also use a string ID if that is
preferred.
(6) Can query cross-namespace if, say, a container manager process is
given an fs_context that hasn't yet been mounted into a namespace - or
hasn't even been fully created yet.
(7) Don't have to create/delete a bunch of sysfs/procfs nodes each time a
mount happens or is removed - and since systemd makes much use of
mount namespaces and mount propagation, this will create a lot of
nodes.
================
DESIGN DECISIONS
================
(1) Information is partitioned into sets of attributes.
(2) Attribute IDs are integers as they're fast to compare.
(3) Attribute values are typed (struct, list of structs, string, opaque
blob). They type is fixed for a particular attribute.
(4) For structure types, the length is also a version. New fields can be
tacked onto the end.
(5) When copying a versioned struct to userspace, the core handles a
version mismatch by truncating or zero-padding the data as necessary.
None of this is seen by the filesystem.
(6) The core handles all the buffering and buffer resizing.
(7) The filesystem never gets any access to the userspace parameter buffer
or result buffer.
(8) "Meta" attributes can describe other attributes.
========
OVERVIEW
========
fsinfo() is a system call that allows information about the filesystem at a
particular path point to be queried as a set of attributes.
Attribute values are of four basic types:
(1) Structure with version-dependent length (the length is the version).
(2) Variable-length string.
(3) List of structures (all the same length).
(4) Opaque blob.
Attributes can have multiple values either as a sequence of values or a
sequence-of-sequences of values and all the values of a particular
attribute must be of the same type. Values can be up to INT_MAX size,
subject to memory availability.
Note that the values of an attribute *are* allowed to vary between dentries
within a single superblock, depending on the specific dentry that you're
looking at, but the values still have to be of the type for that attribute.
I've tried to make the interface as light as possible, so integer attribute
ID rather than string and the core does all the buffer allocation and
expansion and all the extensibility support work rather than leaving that
to the filesystems. This means that userspace pointers are not exposed to
the filesystem.
fsinfo() allows a variety of information to be retrieved about a filesystem
and the mount topology:
(1) General superblock attributes:
- Filesystem identifiers (UUID, volume label, device numbers, ...)
- The limits on a filesystem's capabilities
- Information on supported statx fields and attributes and IOC flags.
- A variety single-bit flags indicating supported capabilities.
- Timestamp resolution and range.
- The amount of space/free space in a filesystem (as statfs()).
- Superblock notification counter.
(2) Filesystem-specific superblock attributes:
- Superblock-level timestamps.
- Cell name, workgroup or other netfs grouping concept.
- Server names and addresses.
(3) VFS information:
- Mount topology information.
- Mount attributes.
- Mount notification counter.
- Mount point path.
(4) Information about what the fsinfo() syscall itself supports, including
the type and struct size of attributes.
The system is extensible:
(1) New attributes can be added. There is no requirement that a
filesystem implement every attribute. A helper function is provided
to scan a list of attributes and a filesystem can have multiple such
lists.
(2) Version length-dependent structure attributes can be made larger and
have additional information tacked on the end, provided it keeps the
layout of the existing fields. If an older process asks for a shorter
structure, it will only be given the bits it asks for. If a newer
process asks for a longer structure on an older kernel, the extra
space will be set to 0. In all cases, the size of the data actually
available is returned.
In essence, the size of a structure is that structure's version: a
smaller size is an earlier version and a later version includes
everything that the earlier version did.
(3) New single-bit capability flags can be added. This is a structure-typed
attribute and, as such, (2) applies. Any bits you wanted but the kernel
doesn't support are automatically set to 0.
fsinfo() may be called like the following, for example:
struct fsinfo_params params = {
.resolve_flags = RESOLVE_NO_TRAILING_SYMLINKS,
.flags = FSINFO_FLAGS_QUERY_PATH,
.request = FSINFO_ATTR_AFS_SERVER_ADDRESSES,
.Nth = 2,
};
struct fsinfo_server_address address;
len = fsinfo(AT_FDCWD, "/afs/grand.central.org/doc", ¶ms,
&address, sizeof(address));
The above example would query an AFS filesystem to retrieve the address
list for the 3rd server, and:
struct fsinfo_params params = {
.resolve_flags = RESOLVE_NO_TRAILING_SYMLINKS,
.flags = FSINFO_FLAGS_QUERY_PATH,
.request = FSINFO_ATTR_NFS_SERVER_NAME;
};
char server_name[256];
len = fsinfo(AT_FDCWD, "/home/dhowells/", ¶ms,
&server_name, sizeof(server_name));
would retrieve the name of the NFS server as a string.
In future, I want to make fsinfo() capable of querying a context created by
fsopen() or fspick(), e.g.:
fd = fsopen("ext4", 0);
struct fsinfo_params params = {
.flags = FSINFO_FLAGS_QUERY_FSCONTEXT,
.request = FSINFO_ATTR_CONFIGURATION;
};
char buffer[65536];
fsinfo(fd, NULL, ¶ms, &buffer, sizeof(buffer));
even if that context doesn't currently have a superblock attached.
The patches can be found here also:
https://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs.git
on branch:
fsinfo-core
===================
SIGNIFICANT CHANGES
===================
ver #18:
(*) Moved the mount and superblock notification patches into a different
branch.
(*) Made superblock configuration (->show_opts), bindmount path
(->show_path) and filesystem statistics (->show_stats) available as
the CONFIGURATION, MOUNT_PATH and FS_STATISTICS attributes.
(*) Made mountpoint device name available, filtered through the superblock
(->show_devname), as the SOURCE attribute.
(*) Made the mountpoint available as a full path as well as a relative
one.
(*) Added more event counters to MOUNT_INFO, including a subtree
notification counter, to make it easier to clean up after a
notification overrun.
(*) Made the event counter value returned by MOUNT_CHILDREN the sum of the
five event counters.
(*) Added a mount uniquifier and added that to the MOUNT_CHILDREN entries
also so that mount ID reuse can be detected.
(*) Merged the SB_NOTIFICATION attribute into the MOUNT_INFO attribute to
avoid duplicate information.
(*) Switched to using the RESOLVE_* flags rather than AT_* flags for
pathwalk control. Added more RESOLVE_* flags.
(*) Used a lock instead of RCU to enumerate children for the
MOUNT_CHILDREN attribute for safety. This is probably worth
revisiting at a later date, however.
ver #17:
(*) Applied comments from Jann Horn, Darrick Wong and Christian Brauner.
(*) Rearranged the order in which fsinfo() does things so that the
superblock operations table can have a function pointer rather than a
table pointer. The ->fsinfo() op is now called at least twice, once
to determine the size of buffer needed and then to retrieve the data.
If the retrieval step indicates yet more space is needed, the buffer
will be expanded and that step repeated.
(*) Merge the element size into the size in the fsinfo_attribute def and
don't set size for strings or opaques. Let a helper work that out.
This means that strings can actually get larger then 4K.
(*) A helper is provided to scan a list of attributes and call the
appropriate get function. This can be called from a filesystem's
->fsinfo() method multiple times. It also handles attribute
enumeration and info querying.
(*) Rearranged the patches to put all the notification patches first.
This allowed some of the bits to be squashed together. At some point,
I'll move the notification patches into a different branch.
ver #16:
(*) Split the features bits out of the fsinfo() core into their own patch
and got rid of the name encoding attributes.
(*) Renamed the 'array' type to 'list' and made AFS use it for returning
server address lists.
(*) Changed the ->fsinfo() method into an ->fsinfo_attributes[] table,
where each attribute has a ->get() method to deal with it. These
tables can then be returned with an fsinfo meta attribute.
(*) Dropped the fscontext query and parameter/description retrieval
attributes for now.
(*) Picked the mount topology attributes into this branch.
(*) Picked the mount notifications into this branch and rebased on top of
notifications-pipe-core.
(*) Picked the superblock notifications into this branch.
(*) Add sample code for Ext4 and NFS.
David
---
David Howells (14):
VFS: Add additional RESOLVE_* flags
fsinfo: Add fsinfo() syscall to query filesystem information
fsinfo: Provide a bitmap of supported features
fsinfo: Allow retrieval of superblock devname, options and stats
fsinfo: Allow fsinfo() to look up a mount object by ID
fsinfo: Add a uniquifier ID to struct mount
fsinfo: Allow mount information to be queried
fsinfo: Allow the mount topology propogation flags to be retrieved
fsinfo: Provide notification overrun handling support
fsinfo: sample: Mount listing program
fsinfo: Add API documentation
fsinfo: Add support for AFS
fsinfo: Example support for Ext4
fsinfo: Example support for NFS
Documentation/filesystems/fsinfo.rst | 564 +++++++++++++++++
arch/alpha/kernel/syscalls/syscall.tbl | 1
arch/arm/tools/syscall.tbl | 1
arch/arm64/include/asm/unistd.h | 2
arch/ia64/kernel/syscalls/syscall.tbl | 1
arch/m68k/kernel/syscalls/syscall.tbl | 1
arch/microblaze/kernel/syscalls/syscall.tbl | 1
arch/mips/kernel/syscalls/syscall_n32.tbl | 1
arch/mips/kernel/syscalls/syscall_n64.tbl | 1
arch/mips/kernel/syscalls/syscall_o32.tbl | 1
arch/parisc/kernel/syscalls/syscall.tbl | 1
arch/powerpc/kernel/syscalls/syscall.tbl | 1
arch/s390/kernel/syscalls/syscall.tbl | 1
arch/sh/kernel/syscalls/syscall.tbl | 1
arch/sparc/kernel/syscalls/syscall.tbl | 1
arch/x86/entry/syscalls/syscall_32.tbl | 1
arch/x86/entry/syscalls/syscall_64.tbl | 1
arch/xtensa/kernel/syscalls/syscall.tbl | 1
fs/Kconfig | 7
fs/Makefile | 1
fs/afs/internal.h | 1
fs/afs/super.c | 218 +++++++
fs/d_path.c | 2
fs/ext4/Makefile | 1
fs/ext4/ext4.h | 6
fs/ext4/fsinfo.c | 45 +
fs/ext4/super.c | 3
fs/fsinfo.c | 720 ++++++++++++++++++++++
fs/internal.h | 13
fs/mount.h | 3
fs/namespace.c | 362 +++++++++++
fs/nfs/Makefile | 1
fs/nfs/fsinfo.c | 230 +++++++
fs/nfs/internal.h | 6
fs/nfs/nfs4super.c | 3
fs/nfs/super.c | 3
fs/open.c | 8
include/linux/fcntl.h | 3
include/linux/fs.h | 4
include/linux/fsinfo.h | 111 +++
include/linux/syscalls.h | 4
include/uapi/asm-generic/unistd.h | 4
include/uapi/linux/fsinfo.h | 360 +++++++++++
include/uapi/linux/mount.h | 10
include/uapi/linux/openat2.h | 8
include/uapi/linux/windows.h | 35 +
kernel/sys_ni.c | 1
samples/vfs/Makefile | 7
samples/vfs/test-fsinfo.c | 880 +++++++++++++++++++++++++++
samples/vfs/test-mntinfo.c | 277 ++++++++
50 files changed, 3905 insertions(+), 14 deletions(-)
create mode 100644 Documentation/filesystems/fsinfo.rst
create mode 100644 fs/ext4/fsinfo.c
create mode 100644 fs/fsinfo.c
create mode 100644 fs/nfs/fsinfo.c
create mode 100644 include/linux/fsinfo.h
create mode 100644 include/uapi/linux/fsinfo.h
create mode 100644 include/uapi/linux/windows.h
create mode 100644 samples/vfs/test-fsinfo.c
create mode 100644 samples/vfs/test-mntinfo.c
^ permalink raw reply
* [PATCH 01/14] VFS: Add additional RESOLVE_* flags [ver #18]
From: David Howells @ 2020-03-09 14:00 UTC (permalink / raw)
To: torvalds, viro
Cc: Stefan Metzmacher, Aleksa Sarai, dhowells, raven, mszeredi,
christian, jannh, darrick.wong, kzak, jlayton, linux-api,
linux-fsdevel, linux-security-module, linux-kernel
In-Reply-To: <158376244589.344135.12925590041630631412.stgit@warthog.procyon.org.uk>
Add additional RESOLVE_* flags to correspond to AT_* flags that aren't
currently implemented:
RESOLVE_NO_TRAILING_SYMLINKS for AT_SYMLINK_NOFOLLOW
RESOLVE_NO_TRAILING_AUTOMOUNTS for AT_NO_AUTOMOUNT
RESOLVE_EMPTY_PATH for AT_EMPTY_PATH
This is necessary for fsinfo() to use RESOLVE_* flags instead of AT_* flags
if the latter are to be considered deprecated for new system calls.
Also make openat2() handle RESOLVE_NO_TRAILING_SYMLINKS.
Automounting is currently forced by doing an open(), so adding support to
openat2() for RESOLVE_NO_TRAILING_AUTOMOUNTS is not trivial.
Reported-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Aleksa Sarai <cyphar@cyphar.com>
---
fs/open.c | 8 +++++---
include/linux/fcntl.h | 3 ++-
include/uapi/linux/openat2.h | 8 +++++++-
3 files changed, 14 insertions(+), 5 deletions(-)
diff --git a/fs/open.c b/fs/open.c
index 0788b3715731..7c38a7605c21 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -977,7 +977,7 @@ inline struct open_how build_open_how(int flags, umode_t mode)
inline int build_open_flags(const struct open_how *how, struct open_flags *op)
{
int flags = how->flags;
- int lookup_flags = 0;
+ int lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
int acc_mode = ACC_MODE(flags);
/* Must never be set by userspace */
@@ -1055,8 +1055,8 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op)
if (flags & O_DIRECTORY)
lookup_flags |= LOOKUP_DIRECTORY;
- if (!(flags & O_NOFOLLOW))
- lookup_flags |= LOOKUP_FOLLOW;
+ if (flags & O_NOFOLLOW)
+ lookup_flags &= ~LOOKUP_FOLLOW;
if (how->resolve & RESOLVE_NO_XDEV)
lookup_flags |= LOOKUP_NO_XDEV;
@@ -1068,6 +1068,8 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op)
lookup_flags |= LOOKUP_BENEATH;
if (how->resolve & RESOLVE_IN_ROOT)
lookup_flags |= LOOKUP_IN_ROOT;
+ if (how->resolve & RESOLVE_NO_TRAILING_SYMLINKS)
+ lookup_flags &= ~LOOKUP_FOLLOW;
op->lookup_flags = lookup_flags;
return 0;
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index 7bcdcf4f6ab2..eacf17a8ca34 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -19,7 +19,8 @@
/* List of all valid flags for the how->resolve argument: */
#define VALID_RESOLVE_FLAGS \
(RESOLVE_NO_XDEV | RESOLVE_NO_MAGICLINKS | RESOLVE_NO_SYMLINKS | \
- RESOLVE_BENEATH | RESOLVE_IN_ROOT)
+ RESOLVE_BENEATH | RESOLVE_IN_ROOT | RESOLVE_NO_TRAILING_SYMLINKS | \
+ RESOLVE_NO_TRAILING_AUTOMOUNTS | RESOLVE_EMPTY_PATH)
/* List of all open_how "versions". */
#define OPEN_HOW_SIZE_VER0 24 /* sizeof first published struct */
diff --git a/include/uapi/linux/openat2.h b/include/uapi/linux/openat2.h
index 58b1eb711360..2647a108f116 100644
--- a/include/uapi/linux/openat2.h
+++ b/include/uapi/linux/openat2.h
@@ -22,7 +22,10 @@ struct open_how {
__u64 resolve;
};
-/* how->resolve flags for openat2(2). */
+/*
+ * Path resolution paths to replace AT_* paths in all new syscalls that would
+ * use them.
+ */
#define RESOLVE_NO_XDEV 0x01 /* Block mount-point crossings
(includes bind-mounts). */
#define RESOLVE_NO_MAGICLINKS 0x02 /* Block traversal through procfs-style
@@ -35,5 +38,8 @@ struct open_how {
#define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".."
be scoped inside the dirfd
(similar to chroot(2)). */
+#define RESOLVE_NO_TRAILING_SYMLINKS 0x20 /* Don't follow trailing symlinks in the path */
+#define RESOLVE_NO_TRAILING_AUTOMOUNTS 0x40 /* Don't follow trailing automounts in the path */
+#define RESOLVE_EMPTY_PATH 0x80 /* Permit a path of "" to indicate the dfd exactly */
#endif /* _UAPI_LINUX_OPENAT2_H */
^ permalink raw reply related
* [PATCH 02/14] fsinfo: Add fsinfo() syscall to query filesystem information [ver #18]
From: David Howells @ 2020-03-09 14:01 UTC (permalink / raw)
To: torvalds, viro
Cc: linux-api, dhowells, raven, mszeredi, christian, jannh,
darrick.wong, kzak, jlayton, linux-api, linux-fsdevel,
linux-security-module, linux-kernel
In-Reply-To: <158376244589.344135.12925590041630631412.stgit@warthog.procyon.org.uk>
Add a system call to allow filesystem information to be queried. A request
value can be given to indicate the desired attribute. Support is provided
for enumerating multi-value attributes.
===============
NEW SYSTEM CALL
===============
The new system call looks like:
int ret = fsinfo(int dfd,
const char *pathname,
const struct fsinfo_params *params,
size_t params_size,
void *result_buffer,
size_t result_buf_size);
The params parameter optionally points to a block of parameters:
struct fsinfo_params {
__u32 resolve_flags;
__u32 flags;
__u32 request;
__u32 Nth;
__u32 Mth;
};
If params is NULL, the default is that params->request is
FSINFO_ATTR_STATFS and all the other fields are 0. params_size indicates
the size of the parameter struct. If the parameter block is short compared
to what the kernel expects, the missing length will be set to 0; if the
parameter block is longer, an error will be given if the excess is not all
zeros.
The object to be queried is specified as follows - part param->flags
indicates the type of reference:
(1) FSINFO_FLAGS_QUERY_PATH - dfd, pathname and at_flags indicate a
filesystem object to query. There is no separate system call
providing an analogue of lstat() - RESOLVE_NO_TRAILING_SYMLINKS should
be set in at_flags instead. RESOLVE_NO_TRAILING_AUTOMOUNTS can also
be used to an allow automount point to be queried without triggering
it.
(2) FSINFO_FLAGS_QUERY_FD - dfd indicates a file descriptor pointing to
the filesystem object to query. pathname should be NULL.
(3) FSINFO_FLAGS_QUERY_MOUNT - pathname indicates the numeric ID of the
mountpoint to query as a string. dfd is used to constrain which
mounts can be accessed. If dfd is AT_FDCWD, the mount must be within
the subtree rooted at chroot, otherwise the mount must be within the
subtree rooted at the directory specified by dfd.
(4) In the future FSINFO_FLAGS_QUERY_FSCONTEXT will be added - dfd will
indicate a context handle fd obtained from fsopen() or fspick(),
allowing that to be queried before the target superblock is attached
to the filesystem or even created.
params->request indicates the attribute/attributes to be queried. This can
be one of:
FSINFO_ATTR_STATFS - statfs-style info
FSINFO_ATTR_IDS - Filesystem IDs
FSINFO_ATTR_LIMITS - Filesystem limits
FSINFO_ATTR_SUPPORTS - Support for statx, ioctl, etc.
FSINFO_ATTR_TIMESTAMP_INFO - Inode timestamp info
FSINFO_ATTR_VOLUME_ID - Volume ID (string)
FSINFO_ATTR_VOLUME_UUID - Volume UUID
FSINFO_ATTR_VOLUME_NAME - Volume name (string)
FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO - Information about attr Nth
FSINFO_ATTR_FSINFO_ATTRIBUTES - List of supported attrs
Some attributes (such as the servers backing a network filesystem) can have
multiple values. These can be enumerated by setting params->Nth and
params->Mth to 0, 1, ... until ENODATA is returned.
result_buffer and result_buf_size point to the reply buffer. The buffer is
filled up to the specified size, even if this means truncating the reply.
The size of the full reply is returned, irrespective of the amount data
that was copied. In future versions, this will allow extra fields to be
tacked on to the end of the reply, but anyone not expecting them will only
get the subset they're expecting. If either buffer of result_buf_size are
0, no copy will take place and the data size will be returned.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-api@vger.kernel.org
---
arch/alpha/kernel/syscalls/syscall.tbl | 1
arch/arm/tools/syscall.tbl | 1
arch/arm64/include/asm/unistd.h | 2
arch/ia64/kernel/syscalls/syscall.tbl | 1
arch/m68k/kernel/syscalls/syscall.tbl | 1
arch/microblaze/kernel/syscalls/syscall.tbl | 1
arch/mips/kernel/syscalls/syscall_n32.tbl | 1
arch/mips/kernel/syscalls/syscall_n64.tbl | 1
arch/mips/kernel/syscalls/syscall_o32.tbl | 1
arch/parisc/kernel/syscalls/syscall.tbl | 1
arch/powerpc/kernel/syscalls/syscall.tbl | 1
arch/s390/kernel/syscalls/syscall.tbl | 1
arch/sh/kernel/syscalls/syscall.tbl | 1
arch/sparc/kernel/syscalls/syscall.tbl | 1
arch/x86/entry/syscalls/syscall_32.tbl | 1
arch/x86/entry/syscalls/syscall_64.tbl | 1
arch/xtensa/kernel/syscalls/syscall.tbl | 1
fs/Kconfig | 7
fs/Makefile | 1
fs/fsinfo.c | 582 +++++++++++++++++++++++++
include/linux/fs.h | 4
include/linux/fsinfo.h | 73 +++
include/linux/syscalls.h | 4
include/uapi/asm-generic/unistd.h | 4
include/uapi/linux/fsinfo.h | 186 ++++++++
kernel/sys_ni.c | 1
samples/vfs/Makefile | 5
samples/vfs/test-fsinfo.c | 633 +++++++++++++++++++++++++++
28 files changed, 1516 insertions(+), 2 deletions(-)
create mode 100644 fs/fsinfo.c
create mode 100644 include/linux/fsinfo.h
create mode 100644 include/uapi/linux/fsinfo.h
create mode 100644 samples/vfs/test-fsinfo.c
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 7c0115af9010..4d0b07dde12d 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -479,3 +479,4 @@
548 common pidfd_getfd sys_pidfd_getfd
549 common watch_mount sys_watch_mount
550 common watch_sb sys_watch_sb
+551 common fsinfo sys_fsinfo
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index f256f009a89f..fdda8382b420 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -453,3 +453,4 @@
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
440 common watch_sb sys_watch_sb
+441 common fsinfo sys_fsinfo
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index bc0f923e0e04..388eeb71cff0 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -38,7 +38,7 @@
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5)
#define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 441
+#define __NR_compat_syscalls 442
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index a4dafc659647..2316e60e031a 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -360,3 +360,4 @@
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
440 common watch_sb sys_watch_sb
+441 common fsinfo sys_fsinfo
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 893fb4151547..efc2723ca91f 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -439,3 +439,4 @@
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
440 common watch_sb sys_watch_sb
+441 common fsinfo sys_fsinfo
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 54aaf0d40c64..745c0f462fce 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -445,3 +445,4 @@
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
440 common watch_sb sys_watch_sb
+441 common fsinfo sys_fsinfo
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index fd34dd0efed0..499f83562a8c 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -378,3 +378,4 @@
438 n32 pidfd_getfd sys_pidfd_getfd
439 n32 watch_mount sys_watch_mount
440 n32 watch_sb sys_watch_sb
+441 n32 fsinfo sys_fsinfo
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index db0f4c0a0a0b..b3188bc3ab3c 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -354,3 +354,4 @@
438 n64 pidfd_getfd sys_pidfd_getfd
439 n64 watch_mount sys_watch_mount
440 n64 watch_sb sys_watch_sb
+441 n64 fsinfo sys_fsinfo
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index ce2e1326de8f..1a3e8ed5e538 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -427,3 +427,4 @@
438 o32 pidfd_getfd sys_pidfd_getfd
439 o32 watch_mount sys_watch_mount
440 o32 watch_sb sys_watch_sb
+441 o32 fsinfo sys_fsinfo
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index 6e4a7c08b64b..2572c215d861 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -437,3 +437,4 @@
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
440 common watch_sb sys_watch_sb
+441 common fsinfo sys_fsinfo
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 08943f3b8206..39d7ac7e918c 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -521,3 +521,4 @@
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
440 common watch_sb sys_watch_sb
+441 common fsinfo sys_fsinfo
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index b3b8529d2b74..ae4cefd3dd1b 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -442,3 +442,4 @@
438 common pidfd_getfd sys_pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount sys_watch_mount
440 common watch_sb sys_watch_sb sys_watch_sb
+441 common fsinfo sys_fsinfo sys_fsinfo
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 89307a20657c..05945b9aee4b 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -442,3 +442,4 @@
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
440 common watch_sb sys_watch_sb
+441 common fsinfo sys_fsinfo
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 4ff841a00450..b71b34d4b45c 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -485,3 +485,4 @@
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
440 common watch_sb sys_watch_sb
+441 common fsinfo sys_fsinfo
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index e2731d295f88..e118ba9aca4c 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -444,3 +444,4 @@
438 i386 pidfd_getfd sys_pidfd_getfd __ia32_sys_pidfd_getfd
439 i386 watch_mount sys_watch_mount __ia32_sys_watch_mount
440 i386 watch_sb sys_watch_sb __ia32_sys_watch_sb
+441 i386 fsinfo sys_fsinfo __ia32_sys_fsinfo
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index f4391176102c..067f247471d0 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -361,6 +361,7 @@
438 common pidfd_getfd __x64_sys_pidfd_getfd
439 common watch_mount __x64_sys_watch_mount
440 common watch_sb __x64_sys_watch_sb
+441 common fsinfo __x64_sys_fsinfo
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 8e7d731ed6cf..e1ec25099d10 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -410,3 +410,4 @@
438 common pidfd_getfd sys_pidfd_getfd
439 common watch_mount sys_watch_mount
440 common watch_sb sys_watch_sb
+441 common fsinfo sys_fsinfo
diff --git a/fs/Kconfig b/fs/Kconfig
index fef1365c23a5..01d0d436b3cd 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -15,6 +15,13 @@ config VALIDATE_FS_PARSER
Enable this to perform validation of the parameter description for a
filesystem when it is registered.
+config FSINFO
+ bool "Enable the fsinfo() system call"
+ help
+ Enable the file system information querying system call to allow
+ comprehensive information to be retrieved about a filesystem,
+ superblock or mount object.
+
if BLOCK
config FS_IOMAP
diff --git a/fs/Makefile b/fs/Makefile
index 4477757780d0..b6bf2424c7f7 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -55,6 +55,7 @@ obj-$(CONFIG_COREDUMP) += coredump.o
obj-$(CONFIG_SYSCTL) += drop_caches.o
obj-$(CONFIG_FHANDLE) += fhandle.o
+obj-$(CONFIG_FSINFO) += fsinfo.o
obj-y += iomap/
obj-y += quota/
diff --git a/fs/fsinfo.c b/fs/fsinfo.c
new file mode 100644
index 000000000000..b7b81e9d7e21
--- /dev/null
+++ b/fs/fsinfo.c
@@ -0,0 +1,582 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Filesystem information query.
+ *
+ * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+#include <linux/syscalls.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/statfs.h>
+#include <linux/security.h>
+#include <linux/uaccess.h>
+#include <linux/fsinfo.h>
+#include <uapi/linux/mount.h>
+#include "internal.h"
+
+/**
+ * fsinfo_string - Store a NUL-terminated string as an fsinfo attribute value.
+ * @s: The string to store (may be NULL)
+ * @ctx: The parameter context
+ */
+int fsinfo_string(const char *s, struct fsinfo_context *ctx)
+{
+ unsigned int len;
+ char *p = ctx->buffer;
+ int ret = 0;
+
+ if (s) {
+ len = min_t(size_t, strlen(s), ctx->buf_size - 1);
+ if (!ctx->want_size_only) {
+ memcpy(p, s, len);
+ p[len] = 0;
+ }
+ ret = len;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(fsinfo_string);
+
+/*
+ * Get basic filesystem stats from statfs.
+ */
+static int fsinfo_generic_statfs(struct path *path, struct fsinfo_context *ctx)
+{
+ struct fsinfo_statfs *p = ctx->buffer;
+ struct kstatfs buf;
+ int ret;
+
+ ret = vfs_statfs(path, &buf);
+ if (ret < 0)
+ return ret;
+
+ p->f_blocks.lo = buf.f_blocks;
+ p->f_bfree.lo = buf.f_bfree;
+ p->f_bavail.lo = buf.f_bavail;
+ p->f_files.lo = buf.f_files;
+ p->f_ffree.lo = buf.f_ffree;
+ p->f_favail.lo = buf.f_ffree;
+ p->f_bsize = buf.f_bsize;
+ p->f_frsize = buf.f_frsize;
+ return sizeof(*p);
+}
+
+static int fsinfo_generic_ids(struct path *path, struct fsinfo_context *ctx)
+{
+ struct fsinfo_ids *p = ctx->buffer;
+ struct super_block *sb;
+ struct kstatfs buf;
+ int ret;
+
+ ret = vfs_statfs(path, &buf);
+ if (ret < 0 && ret != -ENOSYS)
+ return ret;
+ if (ret == 0)
+ memcpy(&p->f_fsid, &buf.f_fsid, sizeof(p->f_fsid));
+
+ sb = path->dentry->d_sb;
+ p->f_fstype = sb->s_magic;
+ p->f_dev_major = MAJOR(sb->s_dev);
+ p->f_dev_minor = MINOR(sb->s_dev);
+ p->f_sb_id = sb->s_unique_id;
+ strlcpy(p->f_fs_name, sb->s_type->name, sizeof(p->f_fs_name));
+ return sizeof(*p);
+}
+
+int fsinfo_generic_limits(struct path *path, struct fsinfo_context *ctx)
+{
+ struct fsinfo_limits *p = ctx->buffer;
+ struct super_block *sb = path->dentry->d_sb;
+
+ p->max_file_size.hi = 0;
+ p->max_file_size.lo = sb->s_maxbytes;
+ p->max_ino.hi = 0;
+ p->max_ino.lo = UINT_MAX;
+ p->max_hard_links = sb->s_max_links;
+ p->max_uid = UINT_MAX;
+ p->max_gid = UINT_MAX;
+ p->max_projid = UINT_MAX;
+ p->max_filename_len = NAME_MAX;
+ p->max_symlink_len = PATH_MAX;
+ p->max_xattr_name_len = XATTR_NAME_MAX;
+ p->max_xattr_body_len = XATTR_SIZE_MAX;
+ p->max_dev_major = 0xffffff;
+ p->max_dev_minor = 0xff;
+ return sizeof(*p);
+}
+EXPORT_SYMBOL(fsinfo_generic_limits);
+
+int fsinfo_generic_supports(struct path *path, struct fsinfo_context *ctx)
+{
+ struct fsinfo_supports *p = ctx->buffer;
+ struct super_block *sb = path->dentry->d_sb;
+
+ p->stx_mask = STATX_BASIC_STATS;
+ if (sb->s_d_op && sb->s_d_op->d_automount)
+ p->stx_attributes |= STATX_ATTR_AUTOMOUNT;
+ return sizeof(*p);
+}
+EXPORT_SYMBOL(fsinfo_generic_supports);
+
+static const struct fsinfo_timestamp_info fsinfo_default_timestamp_info = {
+ .atime = {
+ .minimum = S64_MIN,
+ .maximum = S64_MAX,
+ .gran_mantissa = 1,
+ .gran_exponent = 0,
+ },
+ .mtime = {
+ .minimum = S64_MIN,
+ .maximum = S64_MAX,
+ .gran_mantissa = 1,
+ .gran_exponent = 0,
+ },
+ .ctime = {
+ .minimum = S64_MIN,
+ .maximum = S64_MAX,
+ .gran_mantissa = 1,
+ .gran_exponent = 0,
+ },
+ .btime = {
+ .minimum = S64_MIN,
+ .maximum = S64_MAX,
+ .gran_mantissa = 1,
+ .gran_exponent = 0,
+ },
+};
+
+int fsinfo_generic_timestamp_info(struct path *path, struct fsinfo_context *ctx)
+{
+ struct fsinfo_timestamp_info *p = ctx->buffer;
+ struct super_block *sb = path->dentry->d_sb;
+ s8 exponent;
+
+ *p = fsinfo_default_timestamp_info;
+
+ if (sb->s_time_gran < 1000000000) {
+ if (sb->s_time_gran < 1000)
+ exponent = -9;
+ else if (sb->s_time_gran < 1000000)
+ exponent = -6;
+ else
+ exponent = -3;
+
+ p->atime.gran_exponent = exponent;
+ p->mtime.gran_exponent = exponent;
+ p->ctime.gran_exponent = exponent;
+ p->btime.gran_exponent = exponent;
+ }
+
+ return sizeof(*p);
+}
+EXPORT_SYMBOL(fsinfo_generic_timestamp_info);
+
+static int fsinfo_generic_volume_uuid(struct path *path, struct fsinfo_context *ctx)
+{
+ struct fsinfo_volume_uuid *p = ctx->buffer;
+ struct super_block *sb = path->dentry->d_sb;
+
+ memcpy(p, &sb->s_uuid, sizeof(*p));
+ return sizeof(*p);
+}
+
+static int fsinfo_generic_volume_id(struct path *path, struct fsinfo_context *ctx)
+{
+ return fsinfo_string(path->dentry->d_sb->s_id, ctx);
+}
+
+static const struct fsinfo_attribute fsinfo_common_attributes[] = {
+ FSINFO_VSTRUCT (FSINFO_ATTR_STATFS, fsinfo_generic_statfs),
+ FSINFO_VSTRUCT (FSINFO_ATTR_IDS, fsinfo_generic_ids),
+ FSINFO_VSTRUCT (FSINFO_ATTR_LIMITS, fsinfo_generic_limits),
+ FSINFO_VSTRUCT (FSINFO_ATTR_SUPPORTS, fsinfo_generic_supports),
+ FSINFO_VSTRUCT (FSINFO_ATTR_TIMESTAMP_INFO, fsinfo_generic_timestamp_info),
+ FSINFO_STRING (FSINFO_ATTR_VOLUME_ID, fsinfo_generic_volume_id),
+ FSINFO_VSTRUCT (FSINFO_ATTR_VOLUME_UUID, fsinfo_generic_volume_uuid),
+
+ FSINFO_LIST (FSINFO_ATTR_FSINFO_ATTRIBUTES, (void *)123UL),
+ FSINFO_VSTRUCT_N(FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO, (void *)123UL),
+ {}
+};
+
+/*
+ * Determine an attribute's minimum buffer size and, if the buffer is large
+ * enough, get the attribute value.
+ */
+static int fsinfo_get_this_attribute(struct path *path,
+ struct fsinfo_context *ctx,
+ const struct fsinfo_attribute *attr)
+{
+ int buf_size;
+
+ if (ctx->Nth != 0 && !(attr->flags & (FSINFO_FLAGS_N | FSINFO_FLAGS_NM)))
+ return -ENODATA;
+ if (ctx->Mth != 0 && !(attr->flags & FSINFO_FLAGS_NM))
+ return -ENODATA;
+
+ switch (attr->type) {
+ case FSINFO_TYPE_VSTRUCT:
+ ctx->clear_tail = true;
+ buf_size = attr->size;
+ break;
+ case FSINFO_TYPE_STRING:
+ case FSINFO_TYPE_OPAQUE:
+ case FSINFO_TYPE_LIST:
+ buf_size = 4096;
+ break;
+ default:
+ return -ENOPKG;
+ }
+
+ if (ctx->buf_size < buf_size)
+ return buf_size;
+
+ return attr->get(path, ctx);
+}
+
+static void fsinfo_attributes_insert(struct fsinfo_context *ctx,
+ const struct fsinfo_attribute *attr)
+{
+ __u32 *p = ctx->buffer;
+ unsigned int i;
+
+ if (ctx->usage >= ctx->buf_size ||
+ ctx->buf_size - ctx->usage < sizeof(__u32)) {
+ ctx->usage += sizeof(__u32);
+ return;
+ }
+
+ for (i = 0; i < ctx->usage / sizeof(__u32); i++)
+ if (p[i] == attr->attr_id)
+ return;
+
+ p[i] = attr->attr_id;
+ ctx->usage += sizeof(__u32);
+}
+
+static int fsinfo_list_attributes(struct path *path,
+ struct fsinfo_context *ctx,
+ const struct fsinfo_attribute *attributes)
+{
+ const struct fsinfo_attribute *a;
+
+ for (a = attributes; a->get; a++)
+ fsinfo_attributes_insert(ctx, a);
+ return -EOPNOTSUPP; /* We want to go through all the lists */
+}
+
+static int fsinfo_get_attribute_info(struct path *path,
+ struct fsinfo_context *ctx,
+ const struct fsinfo_attribute *attributes)
+{
+ const struct fsinfo_attribute *a;
+ struct fsinfo_attribute_info *p = ctx->buffer;
+
+ if (!ctx->buf_size)
+ return sizeof(*p);
+
+ for (a = attributes; a->get; a++) {
+ if (a->attr_id == ctx->Nth) {
+ p->attr_id = a->attr_id;
+ p->type = a->type;
+ p->flags = a->flags;
+ p->size = a->size;
+ p->size = a->size;
+ return sizeof(*p);
+ }
+ }
+ return -EOPNOTSUPP; /* We want to go through all the lists */
+}
+
+/**
+ * fsinfo_get_attribute - Look up and handle an attribute
+ * @path: The object to query
+ * @params: Parameters to define a request and place to store result
+ * @attributes: List of attributes to search.
+ *
+ * Look through a list of attributes for one that matches the requested
+ * attribute then call the handler for it.
+ */
+int fsinfo_get_attribute(struct path *path, struct fsinfo_context *ctx,
+ const struct fsinfo_attribute *attributes)
+{
+ const struct fsinfo_attribute *a;
+
+ switch (ctx->requested_attr) {
+ case FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO:
+ return fsinfo_get_attribute_info(path, ctx, attributes);
+ case FSINFO_ATTR_FSINFO_ATTRIBUTES:
+ return fsinfo_list_attributes(path, ctx, attributes);
+ default:
+ for (a = attributes; a->get; a++)
+ if (a->attr_id == ctx->requested_attr)
+ return fsinfo_get_this_attribute(path, ctx, a);
+ return -EOPNOTSUPP;
+ }
+}
+EXPORT_SYMBOL(fsinfo_get_attribute);
+
+/**
+ * generic_fsinfo - Handle an fsinfo attribute generically
+ * @path: The object to query
+ * @params: Parameters to define a request and place to store result
+ */
+static int fsinfo_call(struct path *path, struct fsinfo_context *ctx)
+{
+ int ret;
+
+ if (path->dentry->d_sb->s_op->fsinfo) {
+ ret = path->dentry->d_sb->s_op->fsinfo(path, ctx);
+ if (ret != -EOPNOTSUPP)
+ return ret;
+ }
+ ret = fsinfo_get_attribute(path, ctx, fsinfo_common_attributes);
+ if (ret != -EOPNOTSUPP)
+ return ret;
+
+ switch (ctx->requested_attr) {
+ case FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO:
+ return -ENODATA;
+ case FSINFO_ATTR_FSINFO_ATTRIBUTES:
+ return ctx->usage;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+/**
+ * vfs_fsinfo - Retrieve filesystem information
+ * @path: The object to query
+ * @params: Parameters to define a request and place to store result
+ *
+ * Get an attribute on a filesystem or an object within a filesystem. The
+ * filesystem attribute to be queried is indicated by @ctx->requested_attr, and
+ * if it's a multi-valued attribute, the particular value is selected by
+ * @ctx->Nth and then @ctx->Mth.
+ *
+ * For common attributes, a value may be fabricated if it is not supported by
+ * the filesystem.
+ *
+ * On success, the size of the attribute's value is returned (0 is a valid
+ * size). A buffer will have been allocated and will be pointed to by
+ * @ctx->buffer. The caller must free this with kvfree().
+ *
+ * Errors can also be returned: -ENOMEM if a buffer cannot be allocated, -EPERM
+ * or -EACCES if permission is denied by the LSM, -EOPNOTSUPP if an attribute
+ * doesn't exist for the specified object or -ENODATA if the attribute exists,
+ * but the Nth,Mth value does not exist. -EMSGSIZE indicates that the value is
+ * unmanageable internally and -ENOPKG indicates other internal failure.
+ *
+ * Errors such as -EIO may also come from attempts to access media or servers
+ * to obtain the requested information if it's not immediately to hand.
+ *
+ * [*] Note that the caller may set @ctx->want_size_only if it only wants the
+ * size of the value and not the data. If this is set, a buffer may not be
+ * allocated under some circumstances. This is intended for size query by
+ * userspace.
+ *
+ * [*] Note that @ctx->clear_tail will be returned set if the data should be
+ * padded out with zeros when writing it to userspace.
+ */
+static int vfs_fsinfo(struct path *path, struct fsinfo_context *ctx)
+{
+ struct dentry *dentry = path->dentry;
+ int ret;
+
+ ret = security_sb_statfs(dentry);
+ if (ret)
+ return ret;
+
+ /* Call the handler to find out the buffer size required. */
+ ctx->buf_size = 0;
+ ret = fsinfo_call(path, ctx);
+ if (ret < 0 || ctx->want_size_only)
+ return ret;
+ ctx->buf_size = ret;
+
+ do {
+ /* Allocate a buffer of the requested size. */
+ if (ctx->buf_size > INT_MAX)
+ return -EMSGSIZE;
+ ctx->buffer = kvzalloc(ctx->buf_size, GFP_KERNEL);
+ if (!ctx->buffer)
+ return -ENOMEM;
+
+ ctx->usage = 0;
+ ctx->skip = 0;
+ ret = fsinfo_call(path, ctx);
+ if (IS_ERR_VALUE((long)ret))
+ return ret;
+ if ((unsigned int)ret <= ctx->buf_size)
+ return ret; /* It fitted */
+
+ /* We need to resize the buffer */
+ ctx->buf_size = roundup(ret, PAGE_SIZE);
+ kvfree(ctx->buffer);
+ ctx->buffer = NULL;
+ } while (!signal_pending(current));
+
+ return -ERESTARTSYS;
+}
+
+static int vfs_fsinfo_path(int dfd, const char __user *pathname,
+ unsigned int resolve_flags, struct fsinfo_context *ctx)
+{
+ struct path path;
+ unsigned lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
+ int ret = -EINVAL;
+
+ if (resolve_flags & ~VALID_RESOLVE_FLAGS)
+ return -EINVAL;
+
+ if (resolve_flags & RESOLVE_NO_XDEV)
+ lookup_flags |= LOOKUP_NO_XDEV;
+ if (resolve_flags & RESOLVE_NO_MAGICLINKS)
+ lookup_flags |= LOOKUP_NO_MAGICLINKS;
+ if (resolve_flags & RESOLVE_NO_SYMLINKS)
+ lookup_flags |= LOOKUP_NO_SYMLINKS;
+ if (resolve_flags & RESOLVE_BENEATH)
+ lookup_flags |= LOOKUP_BENEATH;
+ if (resolve_flags & RESOLVE_IN_ROOT)
+ lookup_flags |= LOOKUP_IN_ROOT;
+ if (resolve_flags & RESOLVE_NO_TRAILING_SYMLINKS)
+ lookup_flags &= ~LOOKUP_FOLLOW;
+ if (resolve_flags & RESOLVE_NO_TRAILING_AUTOMOUNTS)
+ lookup_flags &= ~LOOKUP_AUTOMOUNT;
+ if (resolve_flags & RESOLVE_EMPTY_PATH)
+ lookup_flags |= LOOKUP_EMPTY;
+
+retry:
+ ret = user_path_at(dfd, pathname, lookup_flags, &path);
+ if (ret)
+ goto out;
+
+ ret = vfs_fsinfo(&path, ctx);
+ path_put(&path);
+ if (retry_estale(ret, lookup_flags)) {
+ lookup_flags |= LOOKUP_REVAL;
+ goto retry;
+ }
+out:
+ return ret;
+}
+
+static int vfs_fsinfo_fd(unsigned int fd, struct fsinfo_context *ctx)
+{
+ struct fd f = fdget_raw(fd);
+ int ret = -EBADF;
+
+ if (f.file) {
+ ret = vfs_fsinfo(&f.file->f_path, ctx);
+ fdput(f);
+ }
+ return ret;
+}
+
+/**
+ * sys_fsinfo - System call to get filesystem information
+ * @dfd: Base directory to pathwalk from or fd referring to filesystem.
+ * @pathname: Filesystem to query or NULL.
+ * @params: Parameters to define request (NULL: FSINFO_ATTR_STATFS).
+ * @params_size: Size of parameter buffer.
+ * @result_buffer: Result buffer.
+ * @result_buf_size: Size of result buffer.
+ *
+ * Get information on a filesystem. The filesystem attribute to be queried is
+ * indicated by @_params->request, and some of the attributes can have multiple
+ * values, indexed by @_params->Nth and @_params->Mth. If @_params is NULL,
+ * then the 0th fsinfo_attr_statfs attribute is queried. If an attribute does
+ * not exist, EOPNOTSUPP is returned; if the Nth,Mth value does not exist,
+ * ENODATA is returned.
+ *
+ * On success, the size of the attribute's value is returned. If
+ * @result_buf_size is 0 or @result_buffer is NULL, only the size is returned.
+ * If the size of the value is larger than @result_buf_size, it will be
+ * truncated by the copy. If the size of the value is smaller than
+ * @result_buf_size then the excess buffer space will be cleared. The full
+ * size of the value will be returned, irrespective of how much data is
+ * actually placed in the buffer.
+ */
+SYSCALL_DEFINE6(fsinfo,
+ int, dfd,
+ const char __user *, pathname,
+ const struct fsinfo_params __user *, params,
+ size_t, params_size,
+ void __user *, result_buffer,
+ size_t, result_buf_size)
+{
+ struct fsinfo_context ctx;
+ struct fsinfo_params user_params;
+ unsigned int result_size;
+ void *r;
+ int ret;
+
+ if ((!params && params_size) ||
+ ( params && !params_size) ||
+ (!result_buffer && result_buf_size) ||
+ ( result_buffer && !result_buf_size))
+ return -EINVAL;
+ if (result_buf_size > UINT_MAX)
+ return -EOVERFLOW;
+
+ memset(&ctx, 0, sizeof(ctx));
+ ctx.requested_attr = FSINFO_ATTR_STATFS;
+ ctx.flags = FSINFO_FLAGS_QUERY_PATH;
+ ctx.want_size_only = (result_buf_size == 0);
+
+ if (params) {
+ ret = copy_struct_from_user(&user_params, sizeof(user_params),
+ params, params_size);
+ if (ret < 0)
+ return ret;
+ if (user_params.flags & ~FSINFO_FLAGS_QUERY_MASK)
+ return -EINVAL;
+ ctx.flags = user_params.flags;
+ ctx.requested_attr = user_params.request;
+ ctx.Nth = user_params.Nth;
+ ctx.Mth = user_params.Mth;
+ }
+
+ switch (ctx.flags & FSINFO_FLAGS_QUERY_MASK) {
+ case FSINFO_FLAGS_QUERY_PATH:
+ ret = vfs_fsinfo_path(dfd, pathname, user_params.resolve_flags, &ctx);
+ break;
+ case FSINFO_FLAGS_QUERY_FD:
+ if (pathname)
+ return -EINVAL;
+ ret = vfs_fsinfo_fd(dfd, &ctx);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (ret < 0)
+ goto error;
+
+ r = ctx.buffer + ctx.skip;
+ result_size = min_t(size_t, ret, result_buf_size);
+ if (result_size > 0 &&
+ copy_to_user(result_buffer, r, result_size) != 0) {
+ ret = -EFAULT;
+ goto error;
+ }
+
+ /* Clear any part of the buffer that we won't fill if we're putting a
+ * struct in there. Strings, opaque objects and arrays are expected to
+ * be variable length.
+ */
+ if (ctx.clear_tail &&
+ result_buf_size > result_size &&
+ clear_user(result_buffer + result_size,
+ result_buf_size - result_size) != 0) {
+ ret = -EFAULT;
+ goto error;
+ }
+
+error:
+ kvfree(ctx.buffer);
+ return ret;
+}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9181cfcd5265..39178f89a6ad 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -69,6 +69,7 @@ struct fsverity_info;
struct fsverity_operations;
struct fs_context;
struct fs_parameter_spec;
+struct fsinfo_context;
extern void __init inode_init(void);
extern void __init inode_init_early(void);
@@ -1964,6 +1965,9 @@ struct super_operations {
int (*thaw_super) (struct super_block *);
int (*unfreeze_fs) (struct super_block *);
int (*statfs) (struct dentry *, struct kstatfs *);
+#ifdef CONFIG_FSINFO
+ int (*fsinfo)(struct path *, struct fsinfo_context *);
+#endif
int (*remount_fs) (struct super_block *, int *, char *);
void (*umount_begin) (struct super_block *);
diff --git a/include/linux/fsinfo.h b/include/linux/fsinfo.h
new file mode 100644
index 000000000000..bf806669b4fb
--- /dev/null
+++ b/include/linux/fsinfo.h
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Filesystem information query
+ *
+ * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#ifndef _LINUX_FSINFO_H
+#define _LINUX_FSINFO_H
+
+#ifdef CONFIG_FSINFO
+
+#include <uapi/linux/fsinfo.h>
+
+struct path;
+
+#define FSINFO_NORMAL_ATTR_MAX_SIZE 4096
+
+struct fsinfo_context {
+ __u32 flags; /* [in] FSINFO_FLAGS_* */
+ __u32 requested_attr; /* [in] What is being asking for */
+ __u32 Nth; /* [in] Instance of it (some may have multiple) */
+ __u32 Mth; /* [in] Subinstance */
+ bool want_size_only; /* [in] Just want to know the size, not the data */
+ bool clear_tail; /* [out] T if tail of buffer should be cleared */
+ unsigned int skip; /* [out] Number of bytes to skip in buffer */
+ unsigned int usage; /* [tmp] Amount of buffer used (if large) */
+ unsigned int buf_size; /* [tmp] Size of ->buffer[] */
+ void *buffer; /* [out] The reply buffer */
+};
+
+/*
+ * A filesystem information attribute definition.
+ */
+struct fsinfo_attribute {
+ unsigned int attr_id; /* The ID of the attribute */
+ enum fsinfo_value_type type:8; /* The type of the attribute's value(s) */
+ unsigned int flags:8;
+ unsigned int size:16; /* - Value size (FSINFO_STRUCT/LIST) */
+ int (*get)(struct path *path, struct fsinfo_context *params);
+};
+
+#define __FSINFO(A, T, S, G, F) \
+ { .attr_id = A, .type = T, .flags = F, .size = S, .get = G }
+
+#define _FSINFO(A, T, S, G) __FSINFO(A, T, S, G, 0)
+#define _FSINFO_N(A, T, S, G) __FSINFO(A, T, S, G, FSINFO_FLAGS_N)
+#define _FSINFO_NM(A, T, S, G) __FSINFO(A, T, S, G, FSINFO_FLAGS_NM)
+
+#define _FSINFO_VSTRUCT(A,S,G) _FSINFO (A, FSINFO_TYPE_VSTRUCT, sizeof(S), G)
+#define _FSINFO_VSTRUCT_N(A,S,G) _FSINFO_N (A, FSINFO_TYPE_VSTRUCT, sizeof(S), G)
+#define _FSINFO_VSTRUCT_NM(A,S,G) _FSINFO_NM(A, FSINFO_TYPE_VSTRUCT, sizeof(S), G)
+
+#define FSINFO_VSTRUCT(A,G) _FSINFO_VSTRUCT (A, A##__STRUCT, G)
+#define FSINFO_VSTRUCT_N(A,G) _FSINFO_VSTRUCT_N (A, A##__STRUCT, G)
+#define FSINFO_VSTRUCT_NM(A,G) _FSINFO_VSTRUCT_NM(A, A##__STRUCT, G)
+#define FSINFO_STRING(A,G) _FSINFO (A, FSINFO_TYPE_STRING, 0, G)
+#define FSINFO_STRING_N(A,G) _FSINFO_N (A, FSINFO_TYPE_STRING, 0, G)
+#define FSINFO_STRING_NM(A,G) _FSINFO_NM(A, FSINFO_TYPE_STRING, 0, G)
+#define FSINFO_OPAQUE(A,G) _FSINFO (A, FSINFO_TYPE_OPAQUE, 0, G)
+#define FSINFO_LIST(A,G) _FSINFO (A, FSINFO_TYPE_LIST, sizeof(A##__STRUCT), G)
+#define FSINFO_LIST_N(A,G) _FSINFO_N (A, FSINFO_TYPE_LIST, sizeof(A##__STRUCT), G)
+
+extern int fsinfo_string(const char *, struct fsinfo_context *);
+extern int fsinfo_generic_timestamp_info(struct path *, struct fsinfo_context *);
+extern int fsinfo_generic_supports(struct path *, struct fsinfo_context *);
+extern int fsinfo_generic_limits(struct path *, struct fsinfo_context *);
+extern int fsinfo_get_attribute(struct path *, struct fsinfo_context *,
+ const struct fsinfo_attribute *);
+
+#endif /* CONFIG_FSINFO */
+
+#endif /* _LINUX_FSINFO_H */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index c84440d57f52..76064c0807e5 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -47,6 +47,7 @@ struct stat64;
struct statfs;
struct statfs64;
struct statx;
+struct fsinfo_params;
struct __sysctl_args;
struct sysinfo;
struct timespec;
@@ -1007,6 +1008,9 @@ asmlinkage long sys_watch_mount(int dfd, const char __user *path,
unsigned int at_flags, int watch_fd, int watch_id);
asmlinkage long sys_watch_sb(int dfd, const char __user *path,
unsigned int at_flags, int watch_fd, int watch_id);
+asmlinkage long sys_fsinfo(int dfd, const char __user *pathname,
+ struct fsinfo_params __user *params, size_t params_size,
+ void __user *result_buffer, size_t result_buf_size);
/*
* Architecture-specific system calls
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 5bff318b7ffa..7d764f86d3f5 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -859,9 +859,11 @@ __SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
__SYSCALL(__NR_watch_mount, sys_watch_mount)
#define __NR_watch_sb 440
__SYSCALL(__NR_watch_sb, sys_watch_sb)
+#define __NR_fsinfo 441
+__SYSCALL(__NR_fsinfo, sys_fsinfo)
#undef __NR_syscalls
-#define __NR_syscalls 441
+#define __NR_syscalls 442
/*
* 32 bit systems traditionally used different
diff --git a/include/uapi/linux/fsinfo.h b/include/uapi/linux/fsinfo.h
new file mode 100644
index 000000000000..b56ebd525b03
--- /dev/null
+++ b/include/uapi/linux/fsinfo.h
@@ -0,0 +1,186 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* fsinfo() definitions.
+ *
+ * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+#ifndef _UAPI_LINUX_FSINFO_H
+#define _UAPI_LINUX_FSINFO_H
+
+#include <linux/types.h>
+#include <linux/socket.h>
+#include <linux/openat2.h>
+
+/*
+ * The filesystem attributes that can be requested. Note that some attributes
+ * may have multiple instances which can be switched in the parameter block.
+ */
+#define FSINFO_ATTR_STATFS 0x00 /* statfs()-style state */
+#define FSINFO_ATTR_IDS 0x01 /* Filesystem IDs */
+#define FSINFO_ATTR_LIMITS 0x02 /* Filesystem limits */
+#define FSINFO_ATTR_SUPPORTS 0x03 /* What's supported in statx, iocflags, ... */
+#define FSINFO_ATTR_TIMESTAMP_INFO 0x04 /* Inode timestamp info */
+#define FSINFO_ATTR_VOLUME_ID 0x05 /* Volume ID (string) */
+#define FSINFO_ATTR_VOLUME_UUID 0x06 /* Volume UUID (LE uuid) */
+#define FSINFO_ATTR_VOLUME_NAME 0x07 /* Volume name (string) */
+
+#define FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO 0x100 /* Information about attr N (for path) */
+#define FSINFO_ATTR_FSINFO_ATTRIBUTES 0x101 /* List of supported attrs (for path) */
+
+/*
+ * Optional fsinfo() parameter structure.
+ *
+ * If this is not given, it is assumed that fsinfo_attr_statfs instance 0,0 is
+ * desired.
+ */
+struct fsinfo_params {
+ __u32 flags; /* Flags controlling fsinfo() specifically */
+#define FSINFO_FLAGS_QUERY_MASK 0x0007 /* What object should fsinfo() query? */
+#define FSINFO_FLAGS_QUERY_PATH 0x0000 /* - path, specified by dirfd,pathname,AT_EMPTY_PATH */
+#define FSINFO_FLAGS_QUERY_FD 0x0001 /* - fd specified by dirfd */
+ __u32 resolve_flags; /* RESOLVE_* flags */
+ __u32 request; /* ID of requested attribute */
+ __u32 Nth; /* Instance of it (some may have multiple) */
+ __u32 Mth; /* Subinstance of Nth instance */
+};
+
+enum fsinfo_value_type {
+ FSINFO_TYPE_VSTRUCT = 0, /* Version-lengthed struct (up to 4096 bytes) */
+ FSINFO_TYPE_STRING = 1, /* NUL-term var-length string (up to 4095 chars) */
+ FSINFO_TYPE_OPAQUE = 2, /* Opaque blob (unlimited size) */
+ FSINFO_TYPE_LIST = 3, /* List of ints/structs (unlimited size) */
+};
+
+/*
+ * Information struct for fsinfo(FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO).
+ *
+ * This gives information about the attributes supported by fsinfo for the
+ * given path.
+ */
+struct fsinfo_attribute_info {
+ unsigned int attr_id; /* The ID of the attribute */
+ enum fsinfo_value_type type; /* The type of the attribute's value(s) */
+ unsigned int flags;
+#define FSINFO_FLAGS_N 0x01 /* - Attr has a set of values */
+#define FSINFO_FLAGS_NM 0x02 /* - Attr has a set of sets of values */
+ unsigned int size; /* - Value size (FSINFO_STRUCT/FSINFO_LIST) */
+};
+
+#define FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO__STRUCT struct fsinfo_attribute_info
+#define FSINFO_ATTR_FSINFO_ATTRIBUTES__STRUCT __u32
+
+struct fsinfo_u128 {
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN)
+ __u64 hi;
+ __u64 lo;
+#elif defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
+ __u64 lo;
+ __u64 hi;
+#endif
+};
+
+/*
+ * Information struct for fsinfo(FSINFO_ATTR_STATFS).
+ * - This gives extended filesystem information.
+ */
+struct fsinfo_statfs {
+ struct fsinfo_u128 f_blocks; /* Total number of blocks in fs */
+ struct fsinfo_u128 f_bfree; /* Total number of free blocks */
+ struct fsinfo_u128 f_bavail; /* Number of free blocks available to ordinary user */
+ struct fsinfo_u128 f_files; /* Total number of file nodes in fs */
+ struct fsinfo_u128 f_ffree; /* Number of free file nodes */
+ struct fsinfo_u128 f_favail; /* Number of file nodes available to ordinary user */
+ __u64 f_bsize; /* Optimal block size */
+ __u64 f_frsize; /* Fragment size */
+};
+
+#define FSINFO_ATTR_STATFS__STRUCT struct fsinfo_statfs
+
+/*
+ * Information struct for fsinfo(FSINFO_ATTR_IDS).
+ *
+ * List of basic identifiers as is normally found in statfs().
+ */
+struct fsinfo_ids {
+ char f_fs_name[15 + 1]; /* Filesystem name */
+ __u64 f_fsid; /* Short 64-bit Filesystem ID (as statfs) */
+ __u64 f_sb_id; /* Internal superblock ID for sbnotify()/mntnotify() */
+ __u32 f_fstype; /* Filesystem type from linux/magic.h [uncond] */
+ __u32 f_dev_major; /* As st_dev_* from struct statx [uncond] */
+ __u32 f_dev_minor;
+ __u32 __padding[1];
+};
+
+#define FSINFO_ATTR_IDS__STRUCT struct fsinfo_ids
+
+/*
+ * Information struct for fsinfo(FSINFO_ATTR_LIMITS).
+ *
+ * List of supported filesystem limits.
+ */
+struct fsinfo_limits {
+ struct fsinfo_u128 max_file_size; /* Maximum file size */
+ struct fsinfo_u128 max_ino; /* Maximum inode number */
+ __u64 max_uid; /* Maximum UID supported */
+ __u64 max_gid; /* Maximum GID supported */
+ __u64 max_projid; /* Maximum project ID supported */
+ __u64 max_hard_links; /* Maximum number of hard links on a file */
+ __u64 max_xattr_body_len; /* Maximum xattr content length */
+ __u32 max_xattr_name_len; /* Maximum xattr name length */
+ __u32 max_filename_len; /* Maximum filename length */
+ __u32 max_symlink_len; /* Maximum symlink content length */
+ __u32 max_dev_major; /* Maximum device major representable */
+ __u32 max_dev_minor; /* Maximum device minor representable */
+ __u32 __padding[1];
+};
+
+#define FSINFO_ATTR_LIMITS__STRUCT struct fsinfo_limits
+
+/*
+ * Information struct for fsinfo(FSINFO_ATTR_SUPPORTS).
+ *
+ * What's supported in various masks, such as statx() attribute and mask bits
+ * and IOC flags.
+ */
+struct fsinfo_supports {
+ __u64 stx_attributes; /* What statx::stx_attributes are supported */
+ __u32 stx_mask; /* What statx::stx_mask bits are supported */
+ __u32 fs_ioc_getflags; /* What FS_IOC_GETFLAGS may return */
+ __u32 fs_ioc_setflags_set; /* What FS_IOC_SETFLAGS may set */
+ __u32 fs_ioc_setflags_clear; /* What FS_IOC_SETFLAGS may clear */
+ __u32 win_file_attrs; /* What DOS/Windows FILE_* attributes are supported */
+ __u32 __padding[1];
+};
+
+#define FSINFO_ATTR_SUPPORTS__STRUCT struct fsinfo_supports
+
+struct fsinfo_timestamp_one {
+ __s64 minimum; /* Minimum timestamp value in seconds */
+ __s64 maximum; /* Maximum timestamp value in seconds */
+ __u16 gran_mantissa; /* Granularity(secs) = mant * 10^exp */
+ __s8 gran_exponent;
+ __u8 __padding[5];
+};
+
+/*
+ * Information struct for fsinfo(FSINFO_ATTR_TIMESTAMP_INFO).
+ */
+struct fsinfo_timestamp_info {
+ struct fsinfo_timestamp_one atime; /* Access time */
+ struct fsinfo_timestamp_one mtime; /* Modification time */
+ struct fsinfo_timestamp_one ctime; /* Change time */
+ struct fsinfo_timestamp_one btime; /* Birth/creation time */
+};
+
+#define FSINFO_ATTR_TIMESTAMP_INFO__STRUCT struct fsinfo_timestamp_info
+
+/*
+ * Information struct for fsinfo(FSINFO_ATTR_VOLUME_UUID).
+ */
+struct fsinfo_volume_uuid {
+ __u8 uuid[16];
+};
+
+#define FSINFO_ATTR_VOLUME_UUID__STRUCT struct fsinfo_volume_uuid
+
+#endif /* _UAPI_LINUX_FSINFO_H */
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 0ce01f86e5db..519317f3904c 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -51,6 +51,7 @@ COND_SYSCALL_COMPAT(io_pgetevents);
COND_SYSCALL(io_uring_setup);
COND_SYSCALL(io_uring_enter);
COND_SYSCALL(io_uring_register);
+COND_SYSCALL(fsinfo);
/* fs/xattr.c */
diff --git a/samples/vfs/Makefile b/samples/vfs/Makefile
index 65acdde5c117..9159ad1d7fc5 100644
--- a/samples/vfs/Makefile
+++ b/samples/vfs/Makefile
@@ -1,10 +1,15 @@
# SPDX-License-Identifier: GPL-2.0-only
# List of programs to build
+
hostprogs := \
+ test-fsinfo \
test-fsmount \
test-statx
always-y := $(hostprogs)
+HOSTCFLAGS_test-fsinfo.o += -I$(objtree)/usr/include
+HOSTLDLIBS_test-fsinfo += -static -lm
+
HOSTCFLAGS_test-fsmount.o += -I$(objtree)/usr/include
HOSTCFLAGS_test-statx.o += -I$(objtree)/usr/include
diff --git a/samples/vfs/test-fsinfo.c b/samples/vfs/test-fsinfo.c
new file mode 100644
index 000000000000..67aebf9fc9d8
--- /dev/null
+++ b/samples/vfs/test-fsinfo.c
@@ -0,0 +1,633 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Test the fsinfo() system call
+ *
+ * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#define _GNU_SOURCE
+#define _ATFILE_SOURCE
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <string.h>
+#include <unistd.h>
+#include <ctype.h>
+#include <errno.h>
+#include <time.h>
+#include <math.h>
+#include <fcntl.h>
+#include <sys/syscall.h>
+#include <linux/fsinfo.h>
+#include <linux/socket.h>
+#include <sys/stat.h>
+#include <arpa/inet.h>
+
+#ifndef __NR_fsinfo
+#define __NR_fsinfo -1
+#endif
+
+static bool debug = 0;
+static bool list_last;
+
+static __attribute__((unused))
+ssize_t fsinfo(int dfd, const char *filename,
+ struct fsinfo_params *params, size_t params_size,
+ void *result_buffer, size_t result_buf_size)
+{
+ return syscall(__NR_fsinfo, dfd, filename,
+ params, params_size,
+ result_buffer, result_buf_size);
+}
+
+struct fsinfo_attribute {
+ unsigned int attr_id;
+ enum fsinfo_value_type type;
+ unsigned int size;
+ const char *name;
+ void (*dump)(void *reply, unsigned int size);
+};
+
+static const struct fsinfo_attribute fsinfo_attributes[];
+
+static ssize_t get_fsinfo(const char *, const char *, struct fsinfo_params *, void **);
+
+static void dump_hex(unsigned int *data, int from, int to)
+{
+ unsigned offset, print_offset = 1, col = 0;
+
+ from /= 4;
+ to = (to + 3) / 4;
+
+ for (offset = from; offset < to; offset++) {
+ if (print_offset) {
+ printf("%04x: ", offset * 8);
+ print_offset = 0;
+ }
+ printf("%08x", data[offset]);
+ col++;
+ if ((col & 3) == 0) {
+ printf("\n");
+ print_offset = 1;
+ } else {
+ printf(" ");
+ }
+ }
+
+ if (!print_offset)
+ printf("\n");
+}
+
+static void dump_attribute_info(void *reply, unsigned int size)
+{
+ struct fsinfo_attribute_info *attr_info = reply;
+ const struct fsinfo_attribute *attr;
+ char type[32], val_size[32];
+
+ switch (attr_info->type) {
+ case FSINFO_TYPE_VSTRUCT: strcpy(type, "V-STRUCT"); break;
+ case FSINFO_TYPE_STRING: strcpy(type, "STRING"); break;
+ case FSINFO_TYPE_OPAQUE: strcpy(type, "OPAQUE"); break;
+ case FSINFO_TYPE_LIST: strcpy(type, "LIST"); break;
+ default:
+ sprintf(type, "type-%x", attr_info->type);
+ break;
+ }
+
+ if (attr_info->flags & FSINFO_FLAGS_N)
+ strcat(type, " x N");
+ else if (attr_info->flags & FSINFO_FLAGS_NM)
+ strcat(type, " x NM");
+
+ for (attr = fsinfo_attributes; attr->name; attr++)
+ if (attr->attr_id == attr_info->attr_id)
+ break;
+
+ if (attr_info->size)
+ sprintf(val_size, "%u", attr_info->size);
+ else
+ strcpy(val_size, "-");
+
+ printf("%8x %-12s %08x %5s %s\n",
+ attr_info->attr_id,
+ type,
+ attr_info->flags,
+ val_size,
+ attr->name ? attr->name : "");
+}
+
+static void dump_fsinfo_generic_statfs(void *reply, unsigned int size)
+{
+ struct fsinfo_statfs *f = reply;
+
+ printf("\n");
+ printf("\tblocks : n=%llu fr=%llu av=%llu\n",
+ (unsigned long long)f->f_blocks.lo,
+ (unsigned long long)f->f_bfree.lo,
+ (unsigned long long)f->f_bavail.lo);
+
+ printf("\tfiles : n=%llu fr=%llu av=%llu\n",
+ (unsigned long long)f->f_files.lo,
+ (unsigned long long)f->f_ffree.lo,
+ (unsigned long long)f->f_favail.lo);
+ printf("\tbsize : %llu\n", f->f_bsize);
+ printf("\tfrsize : %llu\n", f->f_frsize);
+}
+
+static void dump_fsinfo_generic_ids(void *reply, unsigned int size)
+{
+ struct fsinfo_ids *f = reply;
+
+ printf("\n");
+ printf("\tdev : %02x:%02x\n", f->f_dev_major, f->f_dev_minor);
+ printf("\tfs : type=%x name=%s\n", f->f_fstype, f->f_fs_name);
+ printf("\tfsid : %llx\n", (unsigned long long)f->f_fsid);
+ printf("\tsbid : %llx\n", (unsigned long long)f->f_sb_id);
+}
+
+static void dump_fsinfo_generic_limits(void *reply, unsigned int size)
+{
+ struct fsinfo_limits *f = reply;
+
+ printf("\n");
+ printf("\tmax file size: %llx%016llx\n",
+ (unsigned long long)f->max_file_size.hi,
+ (unsigned long long)f->max_file_size.lo);
+ printf("\tmax ino : %llx%016llx\n",
+ (unsigned long long)f->max_ino.hi,
+ (unsigned long long)f->max_ino.lo);
+ printf("\tmax ids : u=%llx g=%llx p=%llx\n",
+ (unsigned long long)f->max_uid,
+ (unsigned long long)f->max_gid,
+ (unsigned long long)f->max_projid);
+ printf("\tmax dev : maj=%x min=%x\n",
+ f->max_dev_major, f->max_dev_minor);
+ printf("\tmax links : %llx\n",
+ (unsigned long long)f->max_hard_links);
+ printf("\tmax xattr : n=%x b=%llx\n",
+ f->max_xattr_name_len,
+ (unsigned long long)f->max_xattr_body_len);
+ printf("\tmax len : file=%x sym=%x\n",
+ f->max_filename_len, f->max_symlink_len);
+}
+
+static void dump_fsinfo_generic_supports(void *reply, unsigned int size)
+{
+ struct fsinfo_supports *f = reply;
+
+ printf("\n");
+ printf("\tstx_attr : %llx\n", (unsigned long long)f->stx_attributes);
+ printf("\tstx_mask : %x\n", f->stx_mask);
+ printf("\tfs_ioc_*flags: get=%x set=%x clr=%x\n",
+ f->fs_ioc_getflags, f->fs_ioc_setflags_set, f->fs_ioc_setflags_clear);
+ printf("\twin_fattrs : %x\n", f->win_file_attrs);
+}
+
+static void print_time(struct fsinfo_timestamp_one *t, char stamp)
+{
+ printf("\t%ctime : gran=%gs range=%llx-%llx\n",
+ stamp,
+ t->gran_mantissa * pow(10., t->gran_exponent),
+ (long long)t->minimum,
+ (long long)t->maximum);
+}
+
+static void dump_fsinfo_generic_timestamp_info(void *reply, unsigned int size)
+{
+ struct fsinfo_timestamp_info *f = reply;
+
+ printf("\n");
+ print_time(&f->atime, 'a');
+ print_time(&f->mtime, 'm');
+ print_time(&f->ctime, 'c');
+ print_time(&f->btime, 'b');
+}
+
+static void dump_fsinfo_generic_volume_uuid(void *reply, unsigned int size)
+{
+ struct fsinfo_volume_uuid *f = reply;
+
+ printf("%02x%02x%02x%02x-%02x%02x-%02x%02x-%02x%02x"
+ "-%02x%02x%02x%02x%02x%02x\n",
+ f->uuid[ 0], f->uuid[ 1],
+ f->uuid[ 2], f->uuid[ 3],
+ f->uuid[ 4], f->uuid[ 5],
+ f->uuid[ 6], f->uuid[ 7],
+ f->uuid[ 8], f->uuid[ 9],
+ f->uuid[10], f->uuid[11],
+ f->uuid[12], f->uuid[13],
+ f->uuid[14], f->uuid[15]);
+}
+
+static void dump_string(void *reply, unsigned int size)
+{
+ char *s = reply, *p;
+ bool nl = false, last_nl = false;
+
+ p = s;
+ if (size >= 4096) {
+ size = 4096;
+ p[4092] = '.';
+ p[4093] = '.';
+ p[4094] = '.';
+ p[4095] = 0;
+ } else {
+ p[size] = 0;
+ }
+
+ for (p = s; *p; p++) {
+ if (*p == '\n') {
+ last_nl = nl = true;
+ continue;
+ }
+ last_nl = false;
+ if (!isprint(*p) && *p != '\t')
+ *p = '?';
+ }
+
+ if (nl)
+ putchar('\n');
+ printf("%s", s);
+ if (!last_nl)
+ putchar('\n');
+}
+
+#define dump_fsinfo_meta_attribute_info (void *)0x123
+#define dump_fsinfo_meta_attributes (void *)0x123
+
+/*
+ *
+ */
+#define __FSINFO(A, T, S, G, F, N) \
+ { .attr_id = A, .type = T, .size = S, .name = N, .dump = dump_##G }
+
+#define _FSINFO(A,T,S,G,N) __FSINFO(A, T, S, G, 0, N)
+#define _FSINFO_N(A,T,S,G,N) __FSINFO(A, T, S, G, FSINFO_FLAGS_N, N)
+#define _FSINFO_NM(A,T,S,G,N) __FSINFO(A, T, S, G, FSINFO_FLAGS_NM, N)
+
+#define _FSINFO_VSTRUCT(A,S,G,N) _FSINFO (A, FSINFO_TYPE_VSTRUCT, sizeof(S), G, N)
+#define _FSINFO_VSTRUCT_N(A,S,G,N) _FSINFO_N (A, FSINFO_TYPE_VSTRUCT, sizeof(S), G, N)
+#define _FSINFO_VSTRUCT_NM(A,S,G,N) _FSINFO_NM(A, FSINFO_TYPE_VSTRUCT, sizeof(S), G, N)
+
+#define FSINFO_VSTRUCT(A,G) _FSINFO_VSTRUCT (A, A##__STRUCT, G, #A)
+#define FSINFO_VSTRUCT_N(A,G) _FSINFO_VSTRUCT_N (A, A##__STRUCT, G, #A)
+#define FSINFO_VSTRUCT_NM(A,G) _FSINFO_VSTRUCT_NM(A, A##__STRUCT, G, #A)
+#define FSINFO_STRING(A,G) _FSINFO (A, FSINFO_TYPE_STRING, 0, G, #A)
+#define FSINFO_STRING_N(A,G) _FSINFO_N (A, FSINFO_TYPE_STRING, 0, G, #A)
+#define FSINFO_STRING_NM(A,G) _FSINFO_NM(A, FSINFO_TYPE_STRING, 0, G, #A)
+#define FSINFO_OPAQUE(A,G) _FSINFO (A, FSINFO_TYPE_OPAQUE, 0, G, #A)
+#define FSINFO_LIST(A,G) _FSINFO (A, FSINFO_TYPE_LIST, sizeof(A##__STRUCT), G, #A)
+#define FSINFO_LIST_N(A,G) _FSINFO_N (A, FSINFO_TYPE_LIST, sizeof(A##__STRUCT), G, #A)
+
+static const struct fsinfo_attribute fsinfo_attributes[] = {
+ FSINFO_VSTRUCT (FSINFO_ATTR_STATFS, fsinfo_generic_statfs),
+ FSINFO_VSTRUCT (FSINFO_ATTR_IDS, fsinfo_generic_ids),
+ FSINFO_VSTRUCT (FSINFO_ATTR_LIMITS, fsinfo_generic_limits),
+ FSINFO_VSTRUCT (FSINFO_ATTR_SUPPORTS, fsinfo_generic_supports),
+ FSINFO_VSTRUCT (FSINFO_ATTR_TIMESTAMP_INFO, fsinfo_generic_timestamp_info),
+ FSINFO_STRING (FSINFO_ATTR_VOLUME_ID, string),
+ FSINFO_VSTRUCT (FSINFO_ATTR_VOLUME_UUID, fsinfo_generic_volume_uuid),
+ FSINFO_STRING (FSINFO_ATTR_VOLUME_NAME, string),
+ FSINFO_VSTRUCT_N(FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO, fsinfo_meta_attribute_info),
+ FSINFO_LIST (FSINFO_ATTR_FSINFO_ATTRIBUTES, fsinfo_meta_attributes),
+ {}
+};
+
+static void dump_value(unsigned int attr_id,
+ const struct fsinfo_attribute *attr,
+ const struct fsinfo_attribute_info *attr_info,
+ void *reply, unsigned int size)
+{
+ if (!attr || !attr->dump) {
+ printf("<no dumper>\n");
+ return;
+ }
+
+ if (attr->type == FSINFO_TYPE_VSTRUCT && size < attr->size) {
+ printf("<short data %u/%u>\n", size, attr->size);
+ return;
+ }
+
+ attr->dump(reply, size);
+}
+
+static void dump_list(unsigned int attr_id,
+ const struct fsinfo_attribute *attr,
+ const struct fsinfo_attribute_info *attr_info,
+ void *reply, unsigned int size)
+{
+ size_t elem_size = attr_info->size;
+ unsigned int ix = 0;
+
+ printf("\n");
+ if (!attr || !attr->dump) {
+ printf("<no dumper>\n");
+ return;
+ }
+
+ if (attr->type == FSINFO_TYPE_VSTRUCT && size < attr->size) {
+ printf("<short data %u/%u>\n", size, attr->size);
+ return;
+ }
+
+ list_last = false;
+ while (size >= elem_size) {
+ printf("\t[%02x] ", ix);
+ if (size == elem_size)
+ list_last = true;
+ attr->dump(reply, size);
+ reply += elem_size;
+ size -= elem_size;
+ ix++;
+ }
+}
+
+/*
+ * Call fsinfo, expanding the buffer as necessary.
+ */
+static ssize_t get_fsinfo(const char *file, const char *name,
+ struct fsinfo_params *params, void **_r)
+{
+ ssize_t ret;
+ size_t buf_size = 4096;
+ void *r;
+
+ for (;;) {
+ r = malloc(buf_size);
+ if (!r) {
+ perror("malloc");
+ exit(1);
+ }
+ memset(r, 0xbd, buf_size);
+
+ errno = 0;
+ ret = fsinfo(AT_FDCWD, file, params, sizeof(*params), r, buf_size - 1);
+ if (ret == -1)
+ goto error;
+
+ if (ret <= buf_size - 1)
+ break;
+ buf_size = (ret + 4096 - 1) & ~(4096 - 1);
+ }
+
+ if (debug)
+ printf("fsinfo(%s,%s,%u,%u) = %zd\n",
+ file, name, params->Nth, params->Mth, ret);
+
+ ((char *)r)[ret] = 0;
+ *_r = r;
+ return ret;
+
+error:
+ *_r = NULL;
+ free(r);
+ if (debug)
+ printf("fsinfo(%s,%s,%u,%u) = %m\n",
+ file, name, params->Nth, params->Mth);
+ return ret;
+}
+
+/*
+ * Try one subinstance of an attribute.
+ */
+static int try_one(const char *file, struct fsinfo_params *params,
+ const struct fsinfo_attribute_info *attr_info, bool raw)
+{
+ const struct fsinfo_attribute *attr;
+ const char *name;
+ size_t size = 4096;
+ char namebuf[32];
+ void *r;
+
+ for (attr = fsinfo_attributes; attr->name; attr++) {
+ if (attr->attr_id == params->request) {
+ name = attr->name;
+ if (strncmp(name, "fsinfo_generic_", 15) == 0)
+ name += 15;
+ goto found;
+ }
+ }
+
+ sprintf(namebuf, "<unknown-%x>", params->request);
+ name = namebuf;
+ attr = NULL;
+
+found:
+ size = get_fsinfo(file, name, params, &r);
+
+ if (size == -1) {
+ if (errno == ENODATA) {
+ if (!(attr_info->flags & (FSINFO_FLAGS_N | FSINFO_FLAGS_NM)) &&
+ params->Nth == 0 && params->Mth == 0) {
+ fprintf(stderr,
+ "Unexpected ENODATA (0x%x{%u}{%u})\n",
+ params->request, params->Nth, params->Mth);
+ exit(1);
+ }
+ free(r);
+ return (params->Mth == 0) ? 2 : 1;
+ }
+ if (errno == EOPNOTSUPP) {
+ if (params->Nth > 0 || params->Mth > 0) {
+ fprintf(stderr,
+ "Should return -ENODATA (0x%x{%u}{%u})\n",
+ params->request, params->Nth, params->Mth);
+ exit(1);
+ }
+ //printf("\e[33m%s\e[m: <not supported>\n",
+ // fsinfo_attr_names[attr]);
+ free(r);
+ return 2;
+ }
+ perror(file);
+ exit(1);
+ }
+
+ if (raw) {
+ if (size > 4096)
+ size = 4096;
+ dump_hex(r, 0, size);
+ free(r);
+ return 0;
+ }
+
+ switch (attr_info->flags & (FSINFO_FLAGS_N | FSINFO_FLAGS_NM)) {
+ case 0:
+ printf("\e[33m%s\e[m: ", name);
+ break;
+ case FSINFO_FLAGS_N:
+ printf("\e[33m%s{%u}\e[m: ", name, params->Nth);
+ break;
+ case FSINFO_FLAGS_NM:
+ printf("\e[33m%s{%u,%u}\e[m: ", name, params->Nth, params->Mth);
+ break;
+ }
+
+ switch (attr_info->type) {
+ case FSINFO_TYPE_VSTRUCT:
+ case FSINFO_TYPE_STRING:
+ dump_value(params->request, attr, attr_info, r, size);
+ free(r);
+ return 0;
+
+ case FSINFO_TYPE_LIST:
+ dump_list(params->request, attr, attr_info, r, size);
+ free(r);
+ return 0;
+
+ case FSINFO_TYPE_OPAQUE:
+ free(r);
+ return 0;
+
+ default:
+ fprintf(stderr, "Fishy about %u 0x%x,%x,%x\n",
+ params->request, attr_info->type, attr_info->flags, attr_info->size);
+ exit(1);
+ }
+}
+
+static int cmp_u32(const void *a, const void *b)
+{
+ return *(const int *)a - *(const int *)b;
+}
+
+/*
+ *
+ */
+int main(int argc, char **argv)
+{
+ struct fsinfo_attribute_info attr_info;
+ struct fsinfo_params params = {
+ .resolve_flags = RESOLVE_NO_TRAILING_SYMLINKS,
+ .flags = FSINFO_FLAGS_QUERY_PATH,
+ };
+ unsigned int *attrs, ret, nr, i;
+ bool meta = false;
+ int raw = 0, opt, Nth, Mth;
+
+ while ((opt = getopt(argc, argv, "Madlr"))) {
+ switch (opt) {
+ case 'M':
+ meta = true;
+ continue;
+ case 'a':
+ params.resolve_flags |= RESOLVE_NO_TRAILING_AUTOMOUNTS;
+ params.flags = FSINFO_FLAGS_QUERY_PATH;
+ continue;
+ case 'd':
+ debug = true;
+ continue;
+ case 'l':
+ params.resolve_flags &= ~RESOLVE_NO_TRAILING_SYMLINKS;
+ params.flags = FSINFO_FLAGS_QUERY_PATH;
+ continue;
+ case 'r':
+ raw = 1;
+ continue;
+ }
+ break;
+ }
+
+ argc -= optind;
+ argv += optind;
+
+ if (argc != 1) {
+ printf("Format: test-fsinfo [-Madlr] <path>\n");
+ exit(2);
+ }
+
+ /* Retrieve a list of supported attribute IDs */
+ params.request = FSINFO_ATTR_FSINFO_ATTRIBUTES;
+ params.Nth = 0;
+ params.Mth = 0;
+ ret = get_fsinfo(argv[0], "attributes", ¶ms, (void **)&attrs);
+ if (ret == -1) {
+ fprintf(stderr, "Unable to get attribute list: %m\n");
+ exit(1);
+ }
+
+ if (ret % sizeof(attrs[0])) {
+ fprintf(stderr, "Bad length of attribute list (0x%x)\n", ret);
+ exit(2);
+ }
+
+ nr = ret / sizeof(attrs[0]);
+ qsort(attrs, nr, sizeof(attrs[0]), cmp_u32);
+
+ if (meta) {
+ printf("ATTR ID TYPE FLAGS SIZE NAME\n");
+ printf("======== ============ ======== ===== =========\n");
+ for (i = 0; i < nr; i++) {
+ params.request = FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO;
+ params.Nth = attrs[i];
+ params.Mth = 0;
+ ret = fsinfo(AT_FDCWD, argv[0],
+ ¶ms, sizeof(params),
+ &attr_info, sizeof(attr_info));
+ if (ret == -1) {
+ fprintf(stderr, "Can't get info for attribute %x: %m\n", attrs[i]);
+ exit(1);
+ }
+
+ dump_attribute_info(&attr_info, ret);
+ }
+ exit(0);
+ }
+
+ for (i = 0; i < nr; i++) {
+ params.request = FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO;
+ params.Nth = attrs[i];
+ params.Mth = 0;
+ ret = fsinfo(AT_FDCWD, argv[0],
+ ¶ms, sizeof(params),
+ &attr_info, sizeof(attr_info));
+ if (ret == -1) {
+ fprintf(stderr, "Can't get info for attribute %x: %m\n", attrs[i]);
+ exit(1);
+ }
+
+ if (attrs[i] == FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO ||
+ attrs[i] == FSINFO_ATTR_FSINFO_ATTRIBUTES)
+ continue;
+
+ if (attrs[i] != attr_info.attr_id) {
+ fprintf(stderr, "ID for %03x returned %03x\n",
+ attrs[i], attr_info.attr_id);
+ break;
+ }
+ Nth = 0;
+ do {
+ Mth = 0;
+ do {
+ params.request = attrs[i];
+ params.Nth = Nth;
+ params.Mth = Mth;
+
+ switch (try_one(argv[0], ¶ms, &attr_info, raw)) {
+ case 0:
+ continue;
+ case 1:
+ goto done_M;
+ case 2:
+ goto done_N;
+ }
+ } while (++Mth < 100);
+
+ done_M:
+ if (Mth >= 100) {
+ fprintf(stderr, "Fishy: Mth %x[%u][%u]\n", attrs[i], Nth, Mth);
+ break;
+ }
+
+ } while (++Nth < 100);
+
+ done_N:
+ if (Nth >= 100) {
+ fprintf(stderr, "Fishy: Nth %x[%u]\n", attrs[i], Nth);
+ break;
+ }
+ }
+
+ return 0;
+}
^ permalink raw reply related
* [PATCH 03/14] fsinfo: Provide a bitmap of supported features [ver #18]
From: David Howells @ 2020-03-09 14:01 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, raven, mszeredi, christian, jannh, darrick.wong, kzak,
jlayton, linux-api, linux-fsdevel, linux-security-module,
linux-kernel
In-Reply-To: <158376244589.344135.12925590041630631412.stgit@warthog.procyon.org.uk>
Provide a bitmap of features that a filesystem may provide for the path
being queried. Features include such things as:
(1) The general class of filesystem, such as kernel-interface,
block-based, flash-based, network-based.
(2) Supported inode features, such as which timestamps are supported,
whether simple numeric user, group or project IDs are supported and
whether user identification is actually more complex behind the
scenes.
(3) Supported volume features, such as it having a UUID, a name or a
filesystem ID.
(4) Supported filesystem features, such as what types of file are
supported, whether sparse files, extended attributes and quotas are
supported.
(5) Supported interface features, such as whether locking and leases are
supported, what open flags are honoured and how i_version is managed.
For some filesystems, this may be an immutable set and can just be memcpy'd
into the reply buffer.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/fsinfo.c | 30 +++++++++++++++++++
include/linux/fsinfo.h | 38 ++++++++++++++++++++++++
include/uapi/linux/fsinfo.h | 67 ++++++++++++++++++++++++++++++++++++++++++
samples/vfs/test-fsinfo.c | 69 +++++++++++++++++++++++++++++++++++++++++++
4 files changed, 204 insertions(+)
diff --git a/fs/fsinfo.c b/fs/fsinfo.c
index b7b81e9d7e21..662b0edde151 100644
--- a/fs/fsinfo.c
+++ b/fs/fsinfo.c
@@ -121,6 +121,35 @@ int fsinfo_generic_supports(struct path *path, struct fsinfo_context *ctx)
}
EXPORT_SYMBOL(fsinfo_generic_supports);
+int fsinfo_generic_features(struct path *path, struct fsinfo_context *ctx)
+{
+ struct fsinfo_features *p = ctx->buffer;
+ struct super_block *sb = path->dentry->d_sb;
+
+ fsinfo_init_features(p);
+ if (sb->s_mtd)
+ fsinfo_set_feature(p, FSINFO_FEAT_IS_FLASH_FS);
+ else if (sb->s_bdev)
+ fsinfo_set_feature(p, FSINFO_FEAT_IS_BLOCK_FS);
+
+ if (sb->s_quota_types & QTYPE_MASK_USR)
+ fsinfo_set_feature(p, FSINFO_FEAT_USER_QUOTAS);
+ if (sb->s_quota_types & QTYPE_MASK_GRP)
+ fsinfo_set_feature(p, FSINFO_FEAT_GROUP_QUOTAS);
+ if (sb->s_quota_types & QTYPE_MASK_PRJ)
+ fsinfo_set_feature(p, FSINFO_FEAT_PROJECT_QUOTAS);
+ if (sb->s_d_op && sb->s_d_op->d_automount)
+ fsinfo_set_feature(p, FSINFO_FEAT_AUTOMOUNTS);
+ if (sb->s_id[0])
+ fsinfo_set_feature(p, FSINFO_FEAT_VOLUME_ID);
+
+ fsinfo_set_feature(p, FSINFO_FEAT_HAS_ATIME);
+ fsinfo_set_feature(p, FSINFO_FEAT_HAS_CTIME);
+ fsinfo_set_feature(p, FSINFO_FEAT_HAS_MTIME);
+ return sizeof(*p);
+}
+EXPORT_SYMBOL(fsinfo_generic_features);
+
static const struct fsinfo_timestamp_info fsinfo_default_timestamp_info = {
.atime = {
.minimum = S64_MIN,
@@ -196,6 +225,7 @@ static const struct fsinfo_attribute fsinfo_common_attributes[] = {
FSINFO_VSTRUCT (FSINFO_ATTR_TIMESTAMP_INFO, fsinfo_generic_timestamp_info),
FSINFO_STRING (FSINFO_ATTR_VOLUME_ID, fsinfo_generic_volume_id),
FSINFO_VSTRUCT (FSINFO_ATTR_VOLUME_UUID, fsinfo_generic_volume_uuid),
+ FSINFO_VSTRUCT (FSINFO_ATTR_FEATURES, fsinfo_generic_features),
FSINFO_LIST (FSINFO_ATTR_FSINFO_ATTRIBUTES, (void *)123UL),
FSINFO_VSTRUCT_N(FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO, (void *)123UL),
diff --git a/include/linux/fsinfo.h b/include/linux/fsinfo.h
index bf806669b4fb..3f08e61c3270 100644
--- a/include/linux/fsinfo.h
+++ b/include/linux/fsinfo.h
@@ -67,6 +67,44 @@ extern int fsinfo_generic_supports(struct path *, struct fsinfo_context *);
extern int fsinfo_generic_limits(struct path *, struct fsinfo_context *);
extern int fsinfo_get_attribute(struct path *, struct fsinfo_context *,
const struct fsinfo_attribute *);
+extern int fsinfo_generic_features(struct path *, struct fsinfo_context *);
+
+static inline void fsinfo_init_features(struct fsinfo_features *p)
+{
+ p->nr_features = FSINFO_FEAT__NR;
+}
+
+static inline void fsinfo_set_feature(struct fsinfo_features *p,
+ enum fsinfo_feature feature)
+{
+ p->features[feature / 8] |= 1 << (feature % 8);
+}
+
+static inline void fsinfo_clear_feature(struct fsinfo_features *p,
+ enum fsinfo_feature feature)
+{
+ p->features[feature / 8] &= ~(1 << (feature % 8));
+}
+
+/**
+ * fsinfo_set_unix_features - Set standard UNIX features.
+ * @f: The features mask to alter
+ */
+static inline void fsinfo_set_unix_features(struct fsinfo_features *p)
+{
+ fsinfo_set_feature(p, FSINFO_FEAT_UIDS);
+ fsinfo_set_feature(p, FSINFO_FEAT_GIDS);
+ fsinfo_set_feature(p, FSINFO_FEAT_DIRECTORIES);
+ fsinfo_set_feature(p, FSINFO_FEAT_SYMLINKS);
+ fsinfo_set_feature(p, FSINFO_FEAT_HARD_LINKS);
+ fsinfo_set_feature(p, FSINFO_FEAT_DEVICE_FILES);
+ fsinfo_set_feature(p, FSINFO_FEAT_UNIX_SPECIALS);
+ fsinfo_set_feature(p, FSINFO_FEAT_SPARSE);
+ fsinfo_set_feature(p, FSINFO_FEAT_HAS_ATIME);
+ fsinfo_set_feature(p, FSINFO_FEAT_HAS_CTIME);
+ fsinfo_set_feature(p, FSINFO_FEAT_HAS_MTIME);
+ fsinfo_set_feature(p, FSINFO_FEAT_HAS_INODE_NUMBERS);
+}
#endif /* CONFIG_FSINFO */
diff --git a/include/uapi/linux/fsinfo.h b/include/uapi/linux/fsinfo.h
index b56ebd525b03..448378301456 100644
--- a/include/uapi/linux/fsinfo.h
+++ b/include/uapi/linux/fsinfo.h
@@ -23,6 +23,7 @@
#define FSINFO_ATTR_VOLUME_ID 0x05 /* Volume ID (string) */
#define FSINFO_ATTR_VOLUME_UUID 0x06 /* Volume UUID (LE uuid) */
#define FSINFO_ATTR_VOLUME_NAME 0x07 /* Volume name (string) */
+#define FSINFO_ATTR_FEATURES 0x08 /* Filesystem features (bits) */
#define FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO 0x100 /* Information about attr N (for path) */
#define FSINFO_ATTR_FSINFO_ATTRIBUTES 0x101 /* List of supported attrs (for path) */
@@ -154,6 +155,72 @@ struct fsinfo_supports {
#define FSINFO_ATTR_SUPPORTS__STRUCT struct fsinfo_supports
+/*
+ * Information struct for fsinfo(FSINFO_ATTR_FEATURES).
+ *
+ * Bitmask indicating filesystem features where renderable as single bits.
+ */
+enum fsinfo_feature {
+ FSINFO_FEAT_IS_KERNEL_FS = 0, /* fs is kernel-special filesystem */
+ FSINFO_FEAT_IS_BLOCK_FS = 1, /* fs is block-based filesystem */
+ FSINFO_FEAT_IS_FLASH_FS = 2, /* fs is flash filesystem */
+ FSINFO_FEAT_IS_NETWORK_FS = 3, /* fs is network filesystem */
+ FSINFO_FEAT_IS_AUTOMOUNTER_FS = 4, /* fs is automounter special filesystem */
+ FSINFO_FEAT_IS_MEMORY_FS = 5, /* fs is memory-based filesystem */
+ FSINFO_FEAT_AUTOMOUNTS = 6, /* fs supports automounts */
+ FSINFO_FEAT_ADV_LOCKS = 7, /* fs supports advisory file locking */
+ FSINFO_FEAT_MAND_LOCKS = 8, /* fs supports mandatory file locking */
+ FSINFO_FEAT_LEASES = 9, /* fs supports file leases */
+ FSINFO_FEAT_UIDS = 10, /* fs supports numeric uids */
+ FSINFO_FEAT_GIDS = 11, /* fs supports numeric gids */
+ FSINFO_FEAT_PROJIDS = 12, /* fs supports numeric project ids */
+ FSINFO_FEAT_STRING_USER_IDS = 13, /* fs supports string user identifiers */
+ FSINFO_FEAT_GUID_USER_IDS = 14, /* fs supports GUID user identifiers */
+ FSINFO_FEAT_WINDOWS_ATTRS = 15, /* fs has windows attributes */
+ FSINFO_FEAT_USER_QUOTAS = 16, /* fs has per-user quotas */
+ FSINFO_FEAT_GROUP_QUOTAS = 17, /* fs has per-group quotas */
+ FSINFO_FEAT_PROJECT_QUOTAS = 18, /* fs has per-project quotas */
+ FSINFO_FEAT_XATTRS = 19, /* fs has xattrs */
+ FSINFO_FEAT_JOURNAL = 20, /* fs has a journal */
+ FSINFO_FEAT_DATA_IS_JOURNALLED = 21, /* fs is using data journalling */
+ FSINFO_FEAT_O_SYNC = 22, /* fs supports O_SYNC */
+ FSINFO_FEAT_O_DIRECT = 23, /* fs supports O_DIRECT */
+ FSINFO_FEAT_VOLUME_ID = 24, /* fs has a volume ID */
+ FSINFO_FEAT_VOLUME_UUID = 25, /* fs has a volume UUID */
+ FSINFO_FEAT_VOLUME_NAME = 26, /* fs has a volume name */
+ FSINFO_FEAT_VOLUME_FSID = 27, /* fs has a volume FSID */
+ FSINFO_FEAT_IVER_ALL_CHANGE = 28, /* i_version represents data + meta changes */
+ FSINFO_FEAT_IVER_DATA_CHANGE = 29, /* i_version represents data changes only */
+ FSINFO_FEAT_IVER_MONO_INCR = 30, /* i_version incremented monotonically */
+ FSINFO_FEAT_DIRECTORIES = 31, /* fs supports (sub)directories */
+ FSINFO_FEAT_SYMLINKS = 32, /* fs supports symlinks */
+ FSINFO_FEAT_HARD_LINKS = 33, /* fs supports hard links */
+ FSINFO_FEAT_HARD_LINKS_1DIR = 34, /* fs supports hard links in same dir only */
+ FSINFO_FEAT_DEVICE_FILES = 35, /* fs supports bdev, cdev */
+ FSINFO_FEAT_UNIX_SPECIALS = 36, /* fs supports pipe, fifo, socket */
+ FSINFO_FEAT_RESOURCE_FORKS = 37, /* fs supports resource forks/streams */
+ FSINFO_FEAT_NAME_CASE_INDEP = 38, /* Filename case independence is mandatory */
+ FSINFO_FEAT_NAME_NON_UTF8 = 39, /* fs has non-utf8 names */
+ FSINFO_FEAT_NAME_HAS_CODEPAGE = 40, /* fs has a filename codepage */
+ FSINFO_FEAT_SPARSE = 41, /* fs supports sparse files */
+ FSINFO_FEAT_NOT_PERSISTENT = 42, /* fs is not persistent */
+ FSINFO_FEAT_NO_UNIX_MODE = 43, /* fs does not support unix mode bits */
+ FSINFO_FEAT_HAS_ATIME = 44, /* fs supports access time */
+ FSINFO_FEAT_HAS_BTIME = 45, /* fs supports birth/creation time */
+ FSINFO_FEAT_HAS_CTIME = 46, /* fs supports change time */
+ FSINFO_FEAT_HAS_MTIME = 47, /* fs supports modification time */
+ FSINFO_FEAT_HAS_ACL = 48, /* fs supports ACLs of some sort */
+ FSINFO_FEAT_HAS_INODE_NUMBERS = 49, /* fs has inode numbers */
+ FSINFO_FEAT__NR
+};
+
+struct fsinfo_features {
+ __u32 nr_features; /* Number of supported features (FSINFO_FEAT__NR) */
+ __u8 features[(FSINFO_FEAT__NR + 7) / 8];
+};
+
+#define FSINFO_ATTR_FEATURES__STRUCT struct fsinfo_features
+
struct fsinfo_timestamp_one {
__s64 minimum; /* Minimum timestamp value in seconds */
__s64 maximum; /* Maximum timestamp value in seconds */
diff --git a/samples/vfs/test-fsinfo.c b/samples/vfs/test-fsinfo.c
index 67aebf9fc9d8..a48072c77401 100644
--- a/samples/vfs/test-fsinfo.c
+++ b/samples/vfs/test-fsinfo.c
@@ -184,6 +184,74 @@ static void dump_fsinfo_generic_supports(void *reply, unsigned int size)
printf("\twin_fattrs : %x\n", f->win_file_attrs);
}
+#define FSINFO_FEATURE_NAME(C) [FSINFO_FEAT_##C] = #C
+static const char *fsinfo_feature_names[FSINFO_FEAT__NR] = {
+ FSINFO_FEATURE_NAME(IS_KERNEL_FS),
+ FSINFO_FEATURE_NAME(IS_BLOCK_FS),
+ FSINFO_FEATURE_NAME(IS_FLASH_FS),
+ FSINFO_FEATURE_NAME(IS_NETWORK_FS),
+ FSINFO_FEATURE_NAME(IS_AUTOMOUNTER_FS),
+ FSINFO_FEATURE_NAME(IS_MEMORY_FS),
+ FSINFO_FEATURE_NAME(AUTOMOUNTS),
+ FSINFO_FEATURE_NAME(ADV_LOCKS),
+ FSINFO_FEATURE_NAME(MAND_LOCKS),
+ FSINFO_FEATURE_NAME(LEASES),
+ FSINFO_FEATURE_NAME(UIDS),
+ FSINFO_FEATURE_NAME(GIDS),
+ FSINFO_FEATURE_NAME(PROJIDS),
+ FSINFO_FEATURE_NAME(STRING_USER_IDS),
+ FSINFO_FEATURE_NAME(GUID_USER_IDS),
+ FSINFO_FEATURE_NAME(WINDOWS_ATTRS),
+ FSINFO_FEATURE_NAME(USER_QUOTAS),
+ FSINFO_FEATURE_NAME(GROUP_QUOTAS),
+ FSINFO_FEATURE_NAME(PROJECT_QUOTAS),
+ FSINFO_FEATURE_NAME(XATTRS),
+ FSINFO_FEATURE_NAME(JOURNAL),
+ FSINFO_FEATURE_NAME(DATA_IS_JOURNALLED),
+ FSINFO_FEATURE_NAME(O_SYNC),
+ FSINFO_FEATURE_NAME(O_DIRECT),
+ FSINFO_FEATURE_NAME(VOLUME_ID),
+ FSINFO_FEATURE_NAME(VOLUME_UUID),
+ FSINFO_FEATURE_NAME(VOLUME_NAME),
+ FSINFO_FEATURE_NAME(VOLUME_FSID),
+ FSINFO_FEATURE_NAME(IVER_ALL_CHANGE),
+ FSINFO_FEATURE_NAME(IVER_DATA_CHANGE),
+ FSINFO_FEATURE_NAME(IVER_MONO_INCR),
+ FSINFO_FEATURE_NAME(DIRECTORIES),
+ FSINFO_FEATURE_NAME(SYMLINKS),
+ FSINFO_FEATURE_NAME(HARD_LINKS),
+ FSINFO_FEATURE_NAME(HARD_LINKS_1DIR),
+ FSINFO_FEATURE_NAME(DEVICE_FILES),
+ FSINFO_FEATURE_NAME(UNIX_SPECIALS),
+ FSINFO_FEATURE_NAME(RESOURCE_FORKS),
+ FSINFO_FEATURE_NAME(NAME_CASE_INDEP),
+ FSINFO_FEATURE_NAME(NAME_NON_UTF8),
+ FSINFO_FEATURE_NAME(NAME_HAS_CODEPAGE),
+ FSINFO_FEATURE_NAME(SPARSE),
+ FSINFO_FEATURE_NAME(NOT_PERSISTENT),
+ FSINFO_FEATURE_NAME(NO_UNIX_MODE),
+ FSINFO_FEATURE_NAME(HAS_ATIME),
+ FSINFO_FEATURE_NAME(HAS_BTIME),
+ FSINFO_FEATURE_NAME(HAS_CTIME),
+ FSINFO_FEATURE_NAME(HAS_MTIME),
+ FSINFO_FEATURE_NAME(HAS_ACL),
+ FSINFO_FEATURE_NAME(HAS_INODE_NUMBERS),
+};
+
+static void dump_fsinfo_generic_features(void *reply, unsigned int size)
+{
+ struct fsinfo_features *f = reply;
+ int i;
+
+ printf("\n\t");
+ for (i = 0; i < sizeof(f->features); i++)
+ printf("%02x", f->features[i]);
+ printf(" (nr=%u)\n", f->nr_features);
+ for (i = 0; i < FSINFO_FEAT__NR; i++)
+ if (f->features[i / 8] & (1 << (i % 8)))
+ printf("\t- %s\n", fsinfo_feature_names[i]);
+}
+
static void print_time(struct fsinfo_timestamp_one *t, char stamp)
{
printf("\t%ctime : gran=%gs range=%llx-%llx\n",
@@ -285,6 +353,7 @@ static const struct fsinfo_attribute fsinfo_attributes[] = {
FSINFO_VSTRUCT (FSINFO_ATTR_IDS, fsinfo_generic_ids),
FSINFO_VSTRUCT (FSINFO_ATTR_LIMITS, fsinfo_generic_limits),
FSINFO_VSTRUCT (FSINFO_ATTR_SUPPORTS, fsinfo_generic_supports),
+ FSINFO_VSTRUCT (FSINFO_ATTR_FEATURES, fsinfo_generic_features),
FSINFO_VSTRUCT (FSINFO_ATTR_TIMESTAMP_INFO, fsinfo_generic_timestamp_info),
FSINFO_STRING (FSINFO_ATTR_VOLUME_ID, string),
FSINFO_VSTRUCT (FSINFO_ATTR_VOLUME_UUID, fsinfo_generic_volume_uuid),
^ permalink raw reply related
* [PATCH 04/14] fsinfo: Allow retrieval of superblock devname, options and stats [ver #18]
From: David Howells @ 2020-03-09 14:01 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, raven, mszeredi, christian, jannh, darrick.wong, kzak,
jlayton, linux-api, linux-fsdevel, linux-security-module,
linux-kernel
In-Reply-To: <158376244589.344135.12925590041630631412.stgit@warthog.procyon.org.uk>
Provide fsinfo() attributes to retrieve superblock device name, options,
and statistics in string form. The following attributes are defined:
FSINFO_ATTR_SOURCE - Mount-specific device name
FSINFO_ATTR_CONFIGURATION - Mount options
FSINFO_ATTR_FS_STATISTICS - Filesystem statistics
FSINFO_ATTR_SOURCE could be made indexable by params->Nth to handle the
case where there is more than one source (e.g. the bcachefs filesystem).
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/fsinfo.c | 41 +++++++++++++++++++++++++++++++++++++++++
fs/internal.h | 2 ++
fs/namespace.c | 39 +++++++++++++++++++++++++++++++++++++++
include/uapi/linux/fsinfo.h | 3 +++
samples/vfs/test-fsinfo.c | 4 ++++
5 files changed, 89 insertions(+)
diff --git a/fs/fsinfo.c b/fs/fsinfo.c
index 662b0edde151..9562bce5253c 100644
--- a/fs/fsinfo.c
+++ b/fs/fsinfo.c
@@ -217,6 +217,44 @@ static int fsinfo_generic_volume_id(struct path *path, struct fsinfo_context *ct
return fsinfo_string(path->dentry->d_sb->s_id, ctx);
}
+/*
+ * Retrieve the superblock configuration (mount options) as a comma-separated
+ * string. The initial comma is stripped off.
+ */
+static int fsinfo_generic_seq_read(struct path *path, struct fsinfo_context *ctx)
+{
+ struct super_block *sb = path->dentry->d_sb;
+ struct seq_file m = {
+ .buf = ctx->buffer,
+ .size = ctx->buf_size,
+ };
+ int ret = 0;
+
+ switch (ctx->requested_attr) {
+ case FSINFO_ATTR_CONFIGURATION:
+ if (sb->s_op->show_options)
+ ret = sb->s_op->show_options(&m, path->mnt->mnt_root);
+ break;
+
+ case FSINFO_ATTR_FS_STATISTICS:
+ if (sb->s_op->show_stats)
+ ret = sb->s_op->show_stats(&m, path->mnt->mnt_root);
+ break;
+ }
+
+ if (ret < 0)
+ return ret;
+ if (seq_has_overflowed(&m))
+ return ctx->buf_size + PAGE_SIZE;
+ if (ctx->requested_attr == FSINFO_ATTR_CONFIGURATION) {
+ if (m.count > 0 && ((char *)ctx->buffer)[0] == ',') {
+ m.count--;
+ ctx->skip = 1;
+ }
+ }
+ return m.count;
+}
+
static const struct fsinfo_attribute fsinfo_common_attributes[] = {
FSINFO_VSTRUCT (FSINFO_ATTR_STATFS, fsinfo_generic_statfs),
FSINFO_VSTRUCT (FSINFO_ATTR_IDS, fsinfo_generic_ids),
@@ -226,6 +264,9 @@ static const struct fsinfo_attribute fsinfo_common_attributes[] = {
FSINFO_STRING (FSINFO_ATTR_VOLUME_ID, fsinfo_generic_volume_id),
FSINFO_VSTRUCT (FSINFO_ATTR_VOLUME_UUID, fsinfo_generic_volume_uuid),
FSINFO_VSTRUCT (FSINFO_ATTR_FEATURES, fsinfo_generic_features),
+ FSINFO_STRING (FSINFO_ATTR_SOURCE, fsinfo_generic_mount_source),
+ FSINFO_STRING (FSINFO_ATTR_CONFIGURATION, fsinfo_generic_seq_read),
+ FSINFO_STRING (FSINFO_ATTR_FS_STATISTICS, fsinfo_generic_seq_read),
FSINFO_LIST (FSINFO_ATTR_FSINFO_ATTRIBUTES, (void *)123UL),
FSINFO_VSTRUCT_N(FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO, (void *)123UL),
diff --git a/fs/internal.h b/fs/internal.h
index a0d90f23593c..6f2cc77bf38d 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -91,6 +91,8 @@ extern int __mnt_want_write_file(struct file *);
extern void __mnt_drop_write_file(struct file *);
extern void dissolve_on_fput(struct vfsmount *);
+extern int fsinfo_generic_mount_source(struct path *, struct fsinfo_context *);
+
/*
* fs_struct.c
*/
diff --git a/fs/namespace.c b/fs/namespace.c
index 54d237251941..e26e06447993 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -30,6 +30,7 @@
#include <uapi/linux/mount.h>
#include <linux/fs_context.h>
#include <linux/shmem_fs.h>
+#include <linux/fsinfo.h>
#include "pnode.h"
#include "internal.h"
@@ -3997,3 +3998,41 @@ const struct proc_ns_operations mntns_operations = {
.install = mntns_install,
.owner = mntns_owner,
};
+
+#ifdef CONFIG_FSINFO
+static inline void mangle(struct seq_file *m, const char *s)
+{
+ seq_escape(m, s, " \t\n\\");
+}
+
+/*
+ * Return the mount source/device name as seen from this mountpoint. Shared
+ * mounts may vary here and the filesystem is permitted to substitute its own
+ * rendering.
+ */
+int fsinfo_generic_mount_source(struct path *path, struct fsinfo_context *ctx)
+{
+ struct super_block *sb = path->mnt->mnt_sb;
+ struct mount *mnt = real_mount(path->mnt);
+ struct seq_file m = {
+ .buf = ctx->buffer,
+ .size = ctx->buf_size,
+ };
+ int ret;
+
+ if (sb->s_op->show_devname) {
+ ret = sb->s_op->show_devname(&m, mnt->mnt.mnt_root);
+ if (ret < 0)
+ return ret;
+ } else {
+ if (!mnt->mnt_devname)
+ return fsinfo_string("none", ctx);
+ mangle(&m, mnt->mnt_devname);
+ }
+
+ if (seq_has_overflowed(&m))
+ return ctx->buf_size + PAGE_SIZE;
+ return m.count;
+}
+
+#endif /* CONFIG_FSINFO */
diff --git a/include/uapi/linux/fsinfo.h b/include/uapi/linux/fsinfo.h
index 448378301456..253b5213a775 100644
--- a/include/uapi/linux/fsinfo.h
+++ b/include/uapi/linux/fsinfo.h
@@ -24,6 +24,9 @@
#define FSINFO_ATTR_VOLUME_UUID 0x06 /* Volume UUID (LE uuid) */
#define FSINFO_ATTR_VOLUME_NAME 0x07 /* Volume name (string) */
#define FSINFO_ATTR_FEATURES 0x08 /* Filesystem features (bits) */
+#define FSINFO_ATTR_SOURCE 0x09 /* Superblock source/device name (string) */
+#define FSINFO_ATTR_CONFIGURATION 0x0a /* Superblock configuration/options (string) */
+#define FSINFO_ATTR_FS_STATISTICS 0x0b /* Superblock filesystem statistics (string) */
#define FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO 0x100 /* Information about attr N (for path) */
#define FSINFO_ATTR_FSINFO_ATTRIBUTES 0x101 /* List of supported attrs (for path) */
diff --git a/samples/vfs/test-fsinfo.c b/samples/vfs/test-fsinfo.c
index a48072c77401..1002b718cdbc 100644
--- a/samples/vfs/test-fsinfo.c
+++ b/samples/vfs/test-fsinfo.c
@@ -358,6 +358,10 @@ static const struct fsinfo_attribute fsinfo_attributes[] = {
FSINFO_STRING (FSINFO_ATTR_VOLUME_ID, string),
FSINFO_VSTRUCT (FSINFO_ATTR_VOLUME_UUID, fsinfo_generic_volume_uuid),
FSINFO_STRING (FSINFO_ATTR_VOLUME_NAME, string),
+ FSINFO_STRING (FSINFO_ATTR_SOURCE, string),
+ FSINFO_STRING (FSINFO_ATTR_CONFIGURATION, string),
+ FSINFO_STRING (FSINFO_ATTR_FS_STATISTICS, string),
+
FSINFO_VSTRUCT_N(FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO, fsinfo_meta_attribute_info),
FSINFO_LIST (FSINFO_ATTR_FSINFO_ATTRIBUTES, fsinfo_meta_attributes),
{}
^ permalink raw reply related
* [PATCH 05/14] fsinfo: Allow fsinfo() to look up a mount object by ID [ver #18]
From: David Howells @ 2020-03-09 14:01 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, raven, mszeredi, christian, jannh, darrick.wong, kzak,
jlayton, linux-api, linux-fsdevel, linux-security-module,
linux-kernel
In-Reply-To: <158376244589.344135.12925590041630631412.stgit@warthog.procyon.org.uk>
Allow the fsinfo() syscall to look up a mount object by ID rather than by
pathname. This is necessary as there can be multiple mounts stacked up at
the same pathname and there's no way to look through them otherwise.
This is done by passing FSINFO_FLAGS_QUERY_MOUNT to fsinfo() in the
parameters and then passing the mount ID as a string to fsinfo() in place
of the filename:
struct fsinfo_params params = {
.flags = FSINFO_FLAGS_QUERY_MOUNT,
.request = FSINFO_ATTR_IDS,
};
ret = fsinfo(AT_FDCWD, "21", ¶ms, buffer, sizeof(buffer));
The caller is only permitted to query a mount object if the root directory
of that mount connects directly to the current chroot if dfd == AT_FDCWD[*]
or the directory specified by dfd otherwise. Note that this is not
available to the pathwalk of any other syscall.
[*] This needs to be something other than AT_FDCWD, perhaps AT_FDROOT.
[!] This probably needs an LSM hook.
[!] This might want to check the permissions on all the intervening dirs -
but it would have to do that under RCU conditions.
[!] This might want to check a CAP_* flag.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/fsinfo.c | 53 +++++++++++++++++++
fs/internal.h | 1
fs/namespace.c | 117 ++++++++++++++++++++++++++++++++++++++++++-
include/uapi/linux/fsinfo.h | 1
samples/vfs/test-fsinfo.c | 7 ++-
5 files changed, 175 insertions(+), 4 deletions(-)
diff --git a/fs/fsinfo.c b/fs/fsinfo.c
index 9562bce5253c..bafeb73feaf4 100644
--- a/fs/fsinfo.c
+++ b/fs/fsinfo.c
@@ -547,6 +547,56 @@ static int vfs_fsinfo_fd(unsigned int fd, struct fsinfo_context *ctx)
return ret;
}
+/*
+ * Look up the root of a mount object. This allows access to mount objects
+ * (and their attached superblocks) that can't be retrieved by path because
+ * they're entirely covered.
+ *
+ * We only permit access to a mount that has a direct path between either the
+ * dentry pointed to by dfd or to our chroot (if dfd is AT_FDCWD).
+ */
+static int vfs_fsinfo_mount(int dfd, const char __user *filename,
+ struct fsinfo_context *ctx)
+{
+ struct path path;
+ struct fd f = {};
+ char *name;
+ long mnt_id;
+ int ret;
+
+ if (!filename)
+ return -EINVAL;
+
+ name = strndup_user(filename, 32);
+ if (IS_ERR(name))
+ return PTR_ERR(name);
+ ret = kstrtoul(name, 0, &mnt_id);
+ if (ret < 0)
+ goto out_name;
+ if (mnt_id > INT_MAX)
+ goto out_name;
+
+ if (dfd != AT_FDCWD) {
+ ret = -EBADF;
+ f = fdget_raw(dfd);
+ if (!f.file)
+ goto out_name;
+ }
+
+ ret = lookup_mount_object(f.file ? &f.file->f_path : NULL,
+ mnt_id, &path);
+ if (ret < 0)
+ goto out_fd;
+
+ ret = vfs_fsinfo(&path, ctx);
+ path_put(&path);
+out_fd:
+ fdput(f);
+out_name:
+ kfree(name);
+ return ret;
+}
+
/**
* sys_fsinfo - System call to get filesystem information
* @dfd: Base directory to pathwalk from or fd referring to filesystem.
@@ -620,6 +670,9 @@ SYSCALL_DEFINE6(fsinfo,
return -EINVAL;
ret = vfs_fsinfo_fd(dfd, &ctx);
break;
+ case FSINFO_FLAGS_QUERY_MOUNT:
+ ret = vfs_fsinfo_mount(dfd, pathname, &ctx);
+ break;
default:
return -EINVAL;
}
diff --git a/fs/internal.h b/fs/internal.h
index 6f2cc77bf38d..abbd5299e7dc 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -91,6 +91,7 @@ extern int __mnt_want_write_file(struct file *);
extern void __mnt_drop_write_file(struct file *);
extern void dissolve_on_fput(struct vfsmount *);
+extern int lookup_mount_object(struct path *, int, struct path *);
extern int fsinfo_generic_mount_source(struct path *, struct fsinfo_context *);
/*
diff --git a/fs/namespace.c b/fs/namespace.c
index e26e06447993..f33cec5fe885 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -64,7 +64,7 @@ static int __init set_mphash_entries(char *str)
__setup("mphash_entries=", set_mphash_entries);
static u64 event;
-static DEFINE_IDA(mnt_id_ida);
+static DEFINE_IDR(mnt_id_ida);
static DEFINE_IDA(mnt_group_ida);
static struct hlist_head *mount_hashtable __read_mostly;
@@ -105,17 +105,27 @@ static inline struct hlist_head *mp_hash(struct dentry *dentry)
static int mnt_alloc_id(struct mount *mnt)
{
- int res = ida_alloc(&mnt_id_ida, GFP_KERNEL);
+ int res;
+ /* Allocate an ID, but don't set the pointer back to the mount until
+ * later, as once we do that, we have to follow RCU protocols to get
+ * rid of the mount struct.
+ */
+ res = idr_alloc(&mnt_id_ida, NULL, 0, INT_MAX, GFP_KERNEL);
if (res < 0)
return res;
mnt->mnt_id = res;
return 0;
}
+static void mnt_publish_id(struct mount *mnt)
+{
+ idr_replace(&mnt_id_ida, mnt, mnt->mnt_id);
+}
+
static void mnt_free_id(struct mount *mnt)
{
- ida_free(&mnt_id_ida, mnt->mnt_id);
+ idr_remove(&mnt_id_ida, mnt->mnt_id);
}
/*
@@ -959,6 +969,7 @@ struct vfsmount *vfs_create_mount(struct fs_context *fc)
lock_mount_hash();
list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts);
unlock_mount_hash();
+ mnt_publish_id(mnt);
return &mnt->mnt;
}
EXPORT_SYMBOL(vfs_create_mount);
@@ -1052,6 +1063,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
lock_mount_hash();
list_add_tail(&mnt->mnt_instance, &sb->s_mounts);
unlock_mount_hash();
+ mnt_publish_id(mnt);
if ((flag & CL_SLAVE) ||
((flag & CL_SHARED_TO_SLAVE) && IS_MNT_SHARED(old))) {
@@ -4035,4 +4047,103 @@ int fsinfo_generic_mount_source(struct path *path, struct fsinfo_context *ctx)
return m.count;
}
+/*
+ * See if one path point connects directly to another by ancestral relationship
+ * across mountpoints. Must call with the RCU read lock held.
+ */
+static bool are_paths_connected(struct path *ancestor, struct path *to_check)
+{
+ struct mount *mnt, *parent;
+ struct path cursor;
+ unsigned seq;
+ bool connected;
+
+ seq = 0;
+restart:
+ cursor = *to_check;
+
+ read_seqbegin_or_lock(&rename_lock, &seq);
+ while (cursor.mnt != ancestor->mnt) {
+ mnt = real_mount(cursor.mnt);
+ parent = READ_ONCE(mnt->mnt_parent);
+ if (mnt == parent)
+ goto failed;
+ cursor.dentry = READ_ONCE(mnt->mnt_mountpoint);
+ cursor.mnt = &parent->mnt;
+ }
+
+ while (cursor.dentry != ancestor->dentry) {
+ if (cursor.dentry == cursor.mnt->mnt_root ||
+ IS_ROOT(cursor.dentry))
+ goto failed;
+ cursor.dentry = READ_ONCE(cursor.dentry->d_parent);
+ }
+
+ connected = true;
+out:
+ done_seqretry(&rename_lock, seq);
+ return connected;
+
+failed:
+ if (need_seqretry(&rename_lock, seq)) {
+ seq = 1;
+ goto restart;
+ }
+ connected = false;
+ goto out;
+}
+
+/**
+ * lookup_mount_object - Look up a vfsmount object by ID
+ * @root: The mount root must connect backwards to this point (or chroot if NULL).
+ * @id: The ID of the mountpoint.
+ * @_mntpt: Where to return the resulting mountpoint path.
+ *
+ * Look up the root of the mount with the corresponding ID. This is only
+ * permitted if that mount connects directly to the specified root/chroot.
+ */
+int lookup_mount_object(struct path *root, int mnt_id, struct path *_mntpt)
+{
+ struct mount *mnt;
+ struct path stop, mntpt = {};
+ int ret = -EPERM;
+
+ if (!root)
+ get_fs_root(current->fs, &stop);
+ else
+ stop = *root;
+
+ rcu_read_lock();
+ lock_mount_hash();
+ mnt = idr_find(&mnt_id_ida, mnt_id);
+ if (!mnt)
+ goto out_unlock_mh;
+ if (mnt->mnt.mnt_flags & (MNT_SYNC_UMOUNT | MNT_UMOUNT | MNT_DOOMED))
+ goto out_unlock_mh;
+ if (mnt_get_count(mnt) == 0)
+ goto out_unlock_mh;
+ mnt_add_count(mnt, 1);
+ mntpt.mnt = &mnt->mnt;
+ mntpt.dentry = dget(mnt->mnt.mnt_root);
+ unlock_mount_hash();
+
+ if (are_paths_connected(&stop, &mntpt)) {
+ *_mntpt = mntpt;
+ mntpt.mnt = NULL;
+ mntpt.dentry = NULL;
+ ret = 0;
+ }
+
+out_unlock:
+ rcu_read_unlock();
+ if (!root)
+ path_put(&stop);
+ path_put(&mntpt);
+ return ret;
+
+out_unlock_mh:
+ unlock_mount_hash();
+ goto out_unlock;
+}
+
#endif /* CONFIG_FSINFO */
diff --git a/include/uapi/linux/fsinfo.h b/include/uapi/linux/fsinfo.h
index 253b5213a775..491a59e8cc95 100644
--- a/include/uapi/linux/fsinfo.h
+++ b/include/uapi/linux/fsinfo.h
@@ -42,6 +42,7 @@ struct fsinfo_params {
#define FSINFO_FLAGS_QUERY_MASK 0x0007 /* What object should fsinfo() query? */
#define FSINFO_FLAGS_QUERY_PATH 0x0000 /* - path, specified by dirfd,pathname,AT_EMPTY_PATH */
#define FSINFO_FLAGS_QUERY_FD 0x0001 /* - fd specified by dirfd */
+#define FSINFO_FLAGS_QUERY_MOUNT 0x0002 /* - mount object (path=>mount_id, dirfd=>subtree) */
__u32 resolve_flags; /* RESOLVE_* flags */
__u32 request; /* ID of requested attribute */
__u32 Nth; /* Instance of it (some may have multiple) */
diff --git a/samples/vfs/test-fsinfo.c b/samples/vfs/test-fsinfo.c
index 1002b718cdbc..c407bda4134f 100644
--- a/samples/vfs/test-fsinfo.c
+++ b/samples/vfs/test-fsinfo.c
@@ -579,7 +579,7 @@ int main(int argc, char **argv)
bool meta = false;
int raw = 0, opt, Nth, Mth;
- while ((opt = getopt(argc, argv, "Madlr"))) {
+ while ((opt = getopt(argc, argv, "Madmlr"))) {
switch (opt) {
case 'M':
meta = true;
@@ -595,6 +595,10 @@ int main(int argc, char **argv)
params.resolve_flags &= ~RESOLVE_NO_TRAILING_SYMLINKS;
params.flags = FSINFO_FLAGS_QUERY_PATH;
continue;
+ case 'm':
+ params.resolve_flags = 0;
+ params.flags = FSINFO_FLAGS_QUERY_MOUNT;
+ continue;
case 'r':
raw = 1;
continue;
@@ -607,6 +611,7 @@ int main(int argc, char **argv)
if (argc != 1) {
printf("Format: test-fsinfo [-Madlr] <path>\n");
+ printf("Format: test-fsinfo [-Mdr] -m <mnt_id>\n");
exit(2);
}
^ permalink raw reply related
* [PATCH 06/14] fsinfo: Add a uniquifier ID to struct mount [ver #18]
From: David Howells @ 2020-03-09 14:01 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, raven, mszeredi, christian, jannh, darrick.wong, kzak,
jlayton, linux-api, linux-fsdevel, linux-security-module,
linux-kernel
In-Reply-To: <158376244589.344135.12925590041630631412.stgit@warthog.procyon.org.uk>
Add a uniquifier ID to struct mount that is effectively unique over the
kernel lifetime to deal around mnt_id values being reused. This can then
be exported through fsinfo() to allow detection of replacement mounts that
happen to end up with the same mount ID.
The normal mount handle is still used for referring to a particular mount.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/mount.h | 3 +++
fs/namespace.c | 3 +++
2 files changed, 6 insertions(+)
diff --git a/fs/mount.h b/fs/mount.h
index 381f842f3a27..9afbd2a7f692 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -73,6 +73,9 @@ struct mount {
int mnt_expiry_mark; /* true if marked for expiry */
struct hlist_head mnt_pins;
struct hlist_head mnt_stuck_children;
+#ifdef CONFIG_FSINFO
+ u64 mnt_unique_id; /* ID unique over lifetime of kernel */
+#endif
#ifdef CONFIG_MOUNT_NOTIFICATIONS
atomic_t mnt_topology_changes; /* Number of topology changes applied */
atomic_t mnt_attr_changes; /* Number of attribute changes applied */
diff --git a/fs/namespace.c b/fs/namespace.c
index f33cec5fe885..54e8eb93fdd6 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -115,6 +115,9 @@ static int mnt_alloc_id(struct mount *mnt)
if (res < 0)
return res;
mnt->mnt_id = res;
+#ifdef CONFIG_FSINFO
+ vfs_generate_unique_id(&mnt->mnt_unique_id);
+#endif
return 0;
}
^ permalink raw reply related
* [PATCH 07/14] fsinfo: Allow mount information to be queried [ver #18]
From: David Howells @ 2020-03-09 14:01 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, raven, mszeredi, christian, jannh, darrick.wong, kzak,
jlayton, linux-api, linux-fsdevel, linux-security-module,
linux-kernel
In-Reply-To: <158376244589.344135.12925590041630631412.stgit@warthog.procyon.org.uk>
Allow mount information, including information about the topology tree to
be queried with the fsinfo() system call. Setting AT_FSINFO_QUERY_MOUNT
allows overlapping mounts to be queried by indicating that the syscall
should interpet the pathname as a number indicating the mount ID.
To this end, a number of fsinfo() attributes are provided:
(1) FSINFO_ATTR_MOUNT_INFO.
This is a structure providing information about a mount, including:
- Mounted superblock ID (mount ID uniquifier).
- Mount ID (can be used with AT_FSINFO_QUERY_MOUNT).
- Parent mount ID.
- Mount attributes (eg. R/O, NOEXEC).
- Mount change/notification counter.
Note that the parent mount ID is overridden to the ID of the queried
mount if the parent lies outside of the chroot or dfd tree.
(2) FSINFO_ATTR_MOUNT_PATH.
This a string providing information about a bind mount relative the
the root that was bound off, though it may get overridden by the
filesystem (NFS unconditionally sets it to "/", for example).
(3) FSINFO_ATTR_MOUNT_POINT.
This is a string indicating the name of the mountpoint within the
parent mount, limited to the parent's mounted root and the chroot.
(4) FSINFO_ATTR_MOUNT_POINT_FULL.
This is a string indicating the full path of the mountpoint, limited to
the chroot.
(5) FSINFO_ATTR_MOUNT_CHILDREN.
This produces an array of structures, one for each child and capped
with one for the argument mount (checked after listing all the
children). Each element contains the mount ID and the change counter
of the respective mount object.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/d_path.c | 2
fs/fsinfo.c | 14 +++
fs/internal.h | 10 ++
fs/namespace.c | 177 +++++++++++++++++++++++++++++++++++++++++++
include/uapi/linux/fsinfo.h | 36 +++++++++
samples/vfs/test-fsinfo.c | 43 ++++++++++
6 files changed, 281 insertions(+), 1 deletion(-)
diff --git a/fs/d_path.c b/fs/d_path.c
index 0f1fc1743302..4c203f64e45e 100644
--- a/fs/d_path.c
+++ b/fs/d_path.c
@@ -229,7 +229,7 @@ static int prepend_unreachable(char **buffer, int *buflen)
return prepend(buffer, buflen, "(unreachable)", 13);
}
-static void get_fs_root_rcu(struct fs_struct *fs, struct path *root)
+void get_fs_root_rcu(struct fs_struct *fs, struct path *root)
{
unsigned seq;
diff --git a/fs/fsinfo.c b/fs/fsinfo.c
index bafeb73feaf4..6d2bc03998e4 100644
--- a/fs/fsinfo.c
+++ b/fs/fsinfo.c
@@ -236,6 +236,14 @@ static int fsinfo_generic_seq_read(struct path *path, struct fsinfo_context *ctx
ret = sb->s_op->show_options(&m, path->mnt->mnt_root);
break;
+ case FSINFO_ATTR_MOUNT_PATH:
+ if (sb->s_op->show_path) {
+ ret = sb->s_op->show_path(&m, path->mnt->mnt_root);
+ } else {
+ seq_dentry(&m, path->mnt->mnt_root, " \t\n\\");
+ }
+ break;
+
case FSINFO_ATTR_FS_STATISTICS:
if (sb->s_op->show_stats)
ret = sb->s_op->show_stats(&m, path->mnt->mnt_root);
@@ -270,6 +278,12 @@ static const struct fsinfo_attribute fsinfo_common_attributes[] = {
FSINFO_LIST (FSINFO_ATTR_FSINFO_ATTRIBUTES, (void *)123UL),
FSINFO_VSTRUCT_N(FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO, (void *)123UL),
+
+ FSINFO_VSTRUCT (FSINFO_ATTR_MOUNT_INFO, fsinfo_generic_mount_info),
+ FSINFO_STRING (FSINFO_ATTR_MOUNT_PATH, fsinfo_generic_seq_read),
+ FSINFO_STRING (FSINFO_ATTR_MOUNT_POINT, fsinfo_generic_mount_point),
+ FSINFO_STRING (FSINFO_ATTR_MOUNT_POINT_FULL, fsinfo_generic_mount_point_full),
+ FSINFO_LIST (FSINFO_ATTR_MOUNT_CHILDREN, fsinfo_generic_mount_children),
{}
};
diff --git a/fs/internal.h b/fs/internal.h
index abbd5299e7dc..1a318dc85f2f 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -15,6 +15,7 @@ struct mount;
struct shrink_control;
struct fs_context;
struct user_namespace;
+struct fsinfo_context;
/*
* block_dev.c
@@ -47,6 +48,11 @@ extern int __block_write_begin_int(struct page *page, loff_t pos, unsigned len,
*/
extern void __init chrdev_init(void);
+/*
+ * d_path.c
+ */
+extern void get_fs_root_rcu(struct fs_struct *fs, struct path *root);
+
/*
* fs_context.c
*/
@@ -93,6 +99,10 @@ extern void __mnt_drop_write_file(struct file *);
extern void dissolve_on_fput(struct vfsmount *);
extern int lookup_mount_object(struct path *, int, struct path *);
extern int fsinfo_generic_mount_source(struct path *, struct fsinfo_context *);
+extern int fsinfo_generic_mount_info(struct path *, struct fsinfo_context *);
+extern int fsinfo_generic_mount_point(struct path *, struct fsinfo_context *);
+extern int fsinfo_generic_mount_point_full(struct path *, struct fsinfo_context *);
+extern int fsinfo_generic_mount_children(struct path *, struct fsinfo_context *);
/*
* fs_struct.c
diff --git a/fs/namespace.c b/fs/namespace.c
index 54e8eb93fdd6..a6cb8c6b004f 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -4149,4 +4149,181 @@ int lookup_mount_object(struct path *root, int mnt_id, struct path *_mntpt)
goto out_unlock;
}
+/*
+ * Retrieve information about the nominated mount.
+ */
+int fsinfo_generic_mount_info(struct path *path, struct fsinfo_context *ctx)
+{
+ struct fsinfo_mount_info *p = ctx->buffer;
+ struct super_block *sb;
+ struct mount *m;
+ struct path root;
+ unsigned int flags;
+
+ m = real_mount(path->mnt);
+ sb = m->mnt.mnt_sb;
+
+ p->sb_unique_id = sb->s_unique_id;
+ p->mnt_unique_id = m->mnt_unique_id;
+ p->mnt_id = m->mnt_id;
+ p->parent_id = m->mnt_parent->mnt_id;
+
+ get_fs_root(current->fs, &root);
+ if (path->mnt == root.mnt) {
+ p->parent_id = p->mnt_id;
+ } else {
+ rcu_read_lock();
+ if (!are_paths_connected(&root, path))
+ p->parent_id = p->mnt_id;
+ rcu_read_unlock();
+ }
+ if (IS_MNT_SHARED(m))
+ p->group_id = m->mnt_group_id;
+ if (IS_MNT_SLAVE(m)) {
+ int master = m->mnt_master->mnt_group_id;
+ int dom = get_dominating_id(m, &root);
+ p->master_id = master;
+ if (dom && dom != master)
+ p->from_id = dom;
+ }
+ path_put(&root);
+
+ flags = READ_ONCE(m->mnt.mnt_flags);
+ if (flags & MNT_READONLY)
+ p->attr |= MOUNT_ATTR_RDONLY;
+ if (flags & MNT_NOSUID)
+ p->attr |= MOUNT_ATTR_NOSUID;
+ if (flags & MNT_NODEV)
+ p->attr |= MOUNT_ATTR_NODEV;
+ if (flags & MNT_NOEXEC)
+ p->attr |= MOUNT_ATTR_NOEXEC;
+ if (flags & MNT_NODIRATIME)
+ p->attr |= MOUNT_ATTR_NODIRATIME;
+
+ if (flags & MNT_NOATIME)
+ p->attr |= MOUNT_ATTR_NOATIME;
+ else if (flags & MNT_RELATIME)
+ p->attr |= MOUNT_ATTR_RELATIME;
+ else
+ p->attr |= MOUNT_ATTR_STRICTATIME;
+ return sizeof(*p);
+}
+
+/*
+ * Return the path of this mount relative to its parent and clipped to
+ * the current chroot.
+ */
+int fsinfo_generic_mount_point(struct path *path, struct fsinfo_context *ctx)
+{
+ struct mountpoint *mp;
+ struct mount *m, *parent;
+ struct path mountpoint, root;
+ void *p;
+
+ rcu_read_lock();
+
+ m = real_mount(path->mnt);
+ parent = m->mnt_parent;
+ if (parent == m)
+ goto skip;
+ mp = READ_ONCE(m->mnt_mp);
+ if (mp)
+ goto found;
+skip:
+ rcu_read_unlock();
+ return -ENODATA;
+
+found:
+ mountpoint.mnt = &parent->mnt;
+ mountpoint.dentry = READ_ONCE(mp->m_dentry);
+
+ get_fs_root_rcu(current->fs, &root);
+ if (path->mnt == root.mnt) {
+ rcu_read_unlock();
+ return fsinfo_string("/", ctx);
+ }
+
+ if (root.mnt != &parent->mnt) {
+ root.mnt = &parent->mnt;
+ root.dentry = parent->mnt.mnt_root;
+ }
+
+ p = __d_path(&mountpoint, &root, ctx->buffer, ctx->buf_size);
+ rcu_read_unlock();
+
+ if (IS_ERR(p))
+ return PTR_ERR(p);
+ if (!p)
+ return -EPERM;
+
+ ctx->skip = p - ctx->buffer;
+ return (ctx->buffer + ctx->buf_size) - p;
+}
+
+/*
+ * Return the path of this mount from the current chroot.
+ */
+int fsinfo_generic_mount_point_full(struct path *path, struct fsinfo_context *ctx)
+{
+ struct path root;
+ void *p;
+
+ rcu_read_lock();
+ get_fs_root_rcu(current->fs, &root);
+ p = __d_path(path, &root, ctx->buffer, ctx->buf_size);
+ rcu_read_unlock();
+
+ if (IS_ERR(p))
+ return PTR_ERR(p);
+ if (!p)
+ return -EPERM;
+
+ ctx->skip = p - ctx->buffer;
+ return (ctx->buffer + ctx->buf_size) - p;
+}
+
+/*
+ * Store a mount record into the fsinfo buffer.
+ */
+static void fsinfo_store_mount(struct fsinfo_context *ctx, const struct mount *p)
+{
+ struct fsinfo_mount_child record = {};
+ unsigned int usage = ctx->usage;
+
+ if (ctx->usage >= INT_MAX)
+ return;
+ ctx->usage = usage + sizeof(record);
+
+ if (ctx->buffer && ctx->usage <= ctx->buf_size) {
+ record.mnt_unique_id = p->mnt_unique_id;
+ record.mnt_id = p->mnt_id;
+ memcpy(ctx->buffer + usage, &record, sizeof(record));
+ }
+}
+
+/*
+ * Return information about the submounts relative to path.
+ */
+int fsinfo_generic_mount_children(struct path *path, struct fsinfo_context *ctx)
+{
+ struct mount *m, *child;
+
+ m = real_mount(path->mnt);
+
+ read_seqlock_excl(&mount_lock);
+
+ list_for_each_entry_rcu(child, &m->mnt_mounts, mnt_child) {
+ if (child->mnt_parent != m)
+ continue;
+ fsinfo_store_mount(ctx, child);
+ }
+
+ /* End the list with a copy of the parameter mount's details so that
+ * userspace can quickly check for changes.
+ */
+ fsinfo_store_mount(ctx, m);
+ read_sequnlock_excl(&mount_lock);
+ return ctx->usage;
+}
+
#endif /* CONFIG_FSINFO */
diff --git a/include/uapi/linux/fsinfo.h b/include/uapi/linux/fsinfo.h
index 491a59e8cc95..7a8b577f54b7 100644
--- a/include/uapi/linux/fsinfo.h
+++ b/include/uapi/linux/fsinfo.h
@@ -31,6 +31,12 @@
#define FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO 0x100 /* Information about attr N (for path) */
#define FSINFO_ATTR_FSINFO_ATTRIBUTES 0x101 /* List of supported attrs (for path) */
+#define FSINFO_ATTR_MOUNT_INFO 0x200 /* Mount object information */
+#define FSINFO_ATTR_MOUNT_PATH 0x201 /* Bind mount/superblock path (string) */
+#define FSINFO_ATTR_MOUNT_POINT 0x202 /* Relative path of mount in parent (string) */
+#define FSINFO_ATTR_MOUNT_POINT_FULL 0x203 /* Absolute path of mount (string) */
+#define FSINFO_ATTR_MOUNT_CHILDREN 0x204 /* Children of this mount (list) */
+
/*
* Optional fsinfo() parameter structure.
*
@@ -71,6 +77,7 @@ struct fsinfo_attribute_info {
unsigned int size; /* - Value size (FSINFO_STRUCT/FSINFO_LIST) */
};
+#define FSINFO_ATTR_FSINFO_ATTRIBUTES__STRUCT __u32
#define FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO__STRUCT struct fsinfo_attribute_info
#define FSINFO_ATTR_FSINFO_ATTRIBUTES__STRUCT __u32
@@ -84,6 +91,35 @@ struct fsinfo_u128 {
#endif
};
+/*
+ * Information struct for fsinfo(FSINFO_ATTR_MOUNT_INFO).
+ */
+struct fsinfo_mount_info {
+ __u64 sb_unique_id; /* Kernel-lifetime unique superblock ID */
+ __u64 mnt_unique_id; /* Kernel-lifetime unique mount ID */
+ __u32 mnt_id; /* Mount identifier (use with AT_FSINFO_MOUNTID_PATH) */
+ __u32 parent_id; /* Parent mount identifier */
+ __u32 group_id; /* Mount group ID */
+ __u32 master_id; /* Slave master group ID */
+ __u32 from_id; /* Slave propagated from ID */
+ __u32 attr; /* MOUNT_ATTR_* flags */
+ __u32 __padding[1];
+};
+
+#define FSINFO_ATTR_MOUNT_INFO__STRUCT struct fsinfo_mount_info
+
+/*
+ * Information struct element for fsinfo(FSINFO_ATTR_MOUNT_CHILDREN).
+ * - An extra element is placed on the end representing the parent mount.
+ */
+struct fsinfo_mount_child {
+ __u64 mnt_unique_id; /* Kernel-lifetime unique mount ID */
+ __u32 mnt_id; /* Mount identifier (use with AT_FSINFO_MOUNTID_PATH) */
+ __u32 __padding[1];
+};
+
+#define FSINFO_ATTR_MOUNT_CHILDREN__STRUCT struct fsinfo_mount_child
+
/*
* Information struct for fsinfo(FSINFO_ATTR_STATFS).
* - This gives extended filesystem information.
diff --git a/samples/vfs/test-fsinfo.c b/samples/vfs/test-fsinfo.c
index c407bda4134f..2f9fe3b24bca 100644
--- a/samples/vfs/test-fsinfo.c
+++ b/samples/vfs/test-fsinfo.c
@@ -288,6 +288,43 @@ static void dump_fsinfo_generic_volume_uuid(void *reply, unsigned int size)
f->uuid[14], f->uuid[15]);
}
+static void dump_fsinfo_generic_mount_info(void *reply, unsigned int size)
+{
+ struct fsinfo_mount_info *r = reply;
+
+ printf("\n");
+ printf("\tsb_uniq : %llx\n", (unsigned long long)r->sb_unique_id);
+ printf("\tmnt_uniq: %llx\n", (unsigned long long)r->mnt_unique_id);
+ printf("\tmnt_id : %x\n", r->mnt_id);
+ printf("\tparent : %x\n", r->parent_id);
+ printf("\tgroup : %x\n", r->group_id);
+ printf("\tattr : %x\n", r->attr);
+}
+
+static void dump_fsinfo_generic_mount_child(void *reply, unsigned int size)
+{
+ struct fsinfo_mount_child *r = reply;
+ ssize_t mplen;
+ char path[32], *mp;
+
+ struct fsinfo_params params = {
+ .flags = FSINFO_FLAGS_QUERY_MOUNT,
+ .request = FSINFO_ATTR_MOUNT_POINT,
+ };
+
+ if (!list_last) {
+ sprintf(path, "%u", r->mnt_id);
+ mplen = get_fsinfo(path, "FSINFO_ATTR_MOUNT_POINT", ¶ms, (void **)&mp);
+ if (mplen < 0)
+ mp = "-";
+ } else {
+ mp = "<this>";
+ }
+
+ printf("%8x %16llx %s\n",
+ r->mnt_id, (unsigned long long)r->mnt_unique_id, mp);
+}
+
static void dump_string(void *reply, unsigned int size)
{
char *s = reply, *p;
@@ -364,6 +401,12 @@ static const struct fsinfo_attribute fsinfo_attributes[] = {
FSINFO_VSTRUCT_N(FSINFO_ATTR_FSINFO_ATTRIBUTE_INFO, fsinfo_meta_attribute_info),
FSINFO_LIST (FSINFO_ATTR_FSINFO_ATTRIBUTES, fsinfo_meta_attributes),
+
+ FSINFO_VSTRUCT (FSINFO_ATTR_MOUNT_INFO, fsinfo_generic_mount_info),
+ FSINFO_STRING (FSINFO_ATTR_MOUNT_PATH, string),
+ FSINFO_STRING_N (FSINFO_ATTR_MOUNT_POINT, string),
+ FSINFO_STRING_N (FSINFO_ATTR_MOUNT_POINT_FULL, string),
+ FSINFO_LIST (FSINFO_ATTR_MOUNT_CHILDREN, fsinfo_generic_mount_child),
{}
};
^ permalink raw reply related
* [PATCH 08/14] fsinfo: Allow the mount topology propogation flags to be retrieved [ver #18]
From: David Howells @ 2020-03-09 14:02 UTC (permalink / raw)
To: torvalds, viro
Cc: dhowells, raven, mszeredi, christian, jannh, darrick.wong, kzak,
jlayton, linux-api, linux-fsdevel, linux-security-module,
linux-kernel
In-Reply-To: <158376244589.344135.12925590041630631412.stgit@warthog.procyon.org.uk>
Allow the mount topology propogation flags to be retrieved as part of the
FSINFO_ATTR_MOUNT_INFO attributes.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/namespace.c | 7 ++++++-
include/uapi/linux/fsinfo.h | 2 +-
include/uapi/linux/mount.h | 10 +++++++++-
samples/vfs/test-fsinfo.c | 1 +
4 files changed, 17 insertions(+), 3 deletions(-)
diff --git a/fs/namespace.c b/fs/namespace.c
index a6cb8c6b004f..88aef45bcfa8 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -4177,15 +4177,20 @@ int fsinfo_generic_mount_info(struct path *path, struct fsinfo_context *ctx)
p->parent_id = p->mnt_id;
rcu_read_unlock();
}
- if (IS_MNT_SHARED(m))
+ if (IS_MNT_SHARED(m)) {
p->group_id = m->mnt_group_id;
+ p->propagation |= MOUNT_PROPAGATION_SHARED;
+ }
if (IS_MNT_SLAVE(m)) {
int master = m->mnt_master->mnt_group_id;
int dom = get_dominating_id(m, &root);
p->master_id = master;
if (dom && dom != master)
p->from_id = dom;
+ p->propagation |= MOUNT_PROPAGATION_SLAVE;
}
+ if (IS_MNT_UNBINDABLE(m))
+ p->propagation |= MOUNT_PROPAGATION_UNBINDABLE;
path_put(&root);
flags = READ_ONCE(m->mnt.mnt_flags);
diff --git a/include/uapi/linux/fsinfo.h b/include/uapi/linux/fsinfo.h
index 7a8b577f54b7..909d6104933b 100644
--- a/include/uapi/linux/fsinfo.h
+++ b/include/uapi/linux/fsinfo.h
@@ -103,7 +103,7 @@ struct fsinfo_mount_info {
__u32 master_id; /* Slave master group ID */
__u32 from_id; /* Slave propagated from ID */
__u32 attr; /* MOUNT_ATTR_* flags */
- __u32 __padding[1];
+ __u32 propagation; /* MOUNT_PROPAGATION_* flags */
};
#define FSINFO_ATTR_MOUNT_INFO__STRUCT struct fsinfo_mount_info
diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h
index 96a0240f23fe..39e50fe9d8d9 100644
--- a/include/uapi/linux/mount.h
+++ b/include/uapi/linux/mount.h
@@ -105,7 +105,7 @@ enum fsconfig_command {
#define FSMOUNT_CLOEXEC 0x00000001
/*
- * Mount attributes.
+ * Mount object attributes (these are separate to filesystem attributes).
*/
#define MOUNT_ATTR_RDONLY 0x00000001 /* Mount read-only */
#define MOUNT_ATTR_NOSUID 0x00000002 /* Ignore suid and sgid bits */
@@ -117,4 +117,12 @@ enum fsconfig_command {
#define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */
#define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */
+/*
+ * Mount object propogation attributes.
+ */
+#define MOUNT_PROPAGATION_UNBINDABLE 0x00000001 /* Mount is unbindable */
+#define MOUNT_PROPAGATION_SLAVE 0x00000002 /* Mount is slave */
+#define MOUNT_PROPAGATION_PRIVATE 0x00000000 /* Mount is private (ie. not shared) */
+#define MOUNT_PROPAGATION_SHARED 0x00000004 /* Mount is shared */
+
#endif /* _UAPI_LINUX_MOUNT_H */
diff --git a/samples/vfs/test-fsinfo.c b/samples/vfs/test-fsinfo.c
index 2f9fe3b24bca..bdc7ea952630 100644
--- a/samples/vfs/test-fsinfo.c
+++ b/samples/vfs/test-fsinfo.c
@@ -299,6 +299,7 @@ static void dump_fsinfo_generic_mount_info(void *reply, unsigned int size)
printf("\tparent : %x\n", r->parent_id);
printf("\tgroup : %x\n", r->group_id);
printf("\tattr : %x\n", r->attr);
+ printf("\tpropag : %x\n", r->propagation);
}
static void dump_fsinfo_generic_mount_child(void *reply, unsigned int size)
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox