summaryrefslogtreecommitdiff
path: root/kernel/watch_queue.c
diff options
context:
space:
mode:
authorDavid Howells <dhowells@redhat.com>2020-01-14 17:07:11 +0000
committerDavid Howells <dhowells@redhat.com>2020-05-19 15:08:24 +0100
commitc73be61cede5882f9605a852414db559c0ebedfd (patch)
treead099e88740a192887942623c5fe616ee4de5e30 /kernel/watch_queue.c
parentb580b93664f91db8cb503429030df0f1c1e53528 (diff)
pipe: Add general notification queue support
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>
Diffstat (limited to 'kernel/watch_queue.c')
-rw-r--r--kernel/watch_queue.c657
1 files changed, 657 insertions, 0 deletions
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;
+}