summaryrefslogtreecommitdiff
path: root/ipc/mqueue.c
diff options
context:
space:
mode:
Diffstat (limited to 'ipc/mqueue.c')
-rw-r--r--ipc/mqueue.c1234
1 files changed, 729 insertions, 505 deletions
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index ae1996d3c539..c4f6d65596cf 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -6,7 +6,7 @@
*
* Spinlocks: Mohamed Abbas (abbas.mohamed@intel.com)
* Lockless receive & send, fd based notify:
- * Manfred Spraul (manfred@colorfullife.com)
+ * Manfred Spraul (manfred@colorfullife.com)
*
* Audit: George Wilson (ltcgcw@us.ibm.com)
*
@@ -18,6 +18,7 @@
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/mount.h>
+#include <linux/fs_context.h>
#include <linux/namei.h>
#include <linux/sysctl.h>
#include <linux/poll.h>
@@ -35,10 +36,18 @@
#include <linux/ipc_namespace.h>
#include <linux/user_namespace.h>
#include <linux/slab.h>
+#include <linux/sched/wake_q.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/user.h>
#include <net/sock.h>
#include "util.h"
+struct mqueue_fs_context {
+ struct ipc_namespace *ipc_ns;
+ bool newns; /* Set if newly created ipc namespace */
+};
+
#define MQUEUE_MAGIC 0x19800202
#define DIRENT_SIZE 20
#define FILENT_SIZE 80
@@ -47,8 +56,7 @@
#define RECV 1
#define STATE_NONE 0
-#define STATE_PENDING 1
-#define STATE_READY 2
+#define STATE_READY 1
struct posix_msg_tree_node {
struct rb_node rb_node;
@@ -56,6 +64,66 @@ struct posix_msg_tree_node {
int priority;
};
+/*
+ * Locking:
+ *
+ * Accesses to a message queue are synchronized by acquiring info->lock.
+ *
+ * There are two notable exceptions:
+ * - The actual wakeup of a sleeping task is performed using the wake_q
+ * framework. info->lock is already released when wake_up_q is called.
+ * - The exit codepaths after sleeping check ext_wait_queue->state without
+ * any locks. If it is STATE_READY, then the syscall is completed without
+ * acquiring info->lock.
+ *
+ * MQ_BARRIER:
+ * To achieve proper release/acquire memory barrier pairing, the state is set to
+ * STATE_READY with smp_store_release(), and it is read with READ_ONCE followed
+ * by smp_acquire__after_ctrl_dep(). In addition, wake_q_add_safe() is used.
+ *
+ * This prevents the following races:
+ *
+ * 1) With the simple wake_q_add(), the task could be gone already before
+ * the increase of the reference happens
+ * Thread A
+ * Thread B
+ * WRITE_ONCE(wait.state, STATE_NONE);
+ * schedule_hrtimeout()
+ * wake_q_add(A)
+ * if (cmpxchg()) // success
+ * ->state = STATE_READY (reordered)
+ * <timeout returns>
+ * if (wait.state == STATE_READY) return;
+ * sysret to user space
+ * sys_exit()
+ * get_task_struct() // UaF
+ *
+ * Solution: Use wake_q_add_safe() and perform the get_task_struct() before
+ * the smp_store_release() that does ->state = STATE_READY.
+ *
+ * 2) Without proper _release/_acquire barriers, the woken up task
+ * could read stale data
+ *
+ * Thread A
+ * Thread B
+ * do_mq_timedreceive
+ * WRITE_ONCE(wait.state, STATE_NONE);
+ * schedule_hrtimeout()
+ * state = STATE_READY;
+ * <timeout returns>
+ * if (wait.state == STATE_READY) return;
+ * msg_ptr = wait.msg; // Access to stale data!
+ * receiver->msg = message; (reordered)
+ *
+ * Solution: use _release and _acquire barriers.
+ *
+ * 3) There is intentionally no barrier when setting current->state
+ * to TASK_INTERRUPTIBLE: spin_unlock(&info->lock) provides the
+ * release memory barrier, and the wakeup is triggered when holding
+ * info->lock, i.e. spin_lock(&info->lock) provided a pairing
+ * acquire memory barrier.
+ */
+
struct ext_wait_queue { /* queue of sleeping tasks */
struct task_struct *task;
struct list_head list;
@@ -69,13 +137,15 @@ struct mqueue_inode_info {
wait_queue_head_t wait_q;
struct rb_root msg_tree;
+ struct rb_node *msg_tree_rightmost;
struct posix_msg_tree_node *node_cache;
struct mq_attr attr;
struct sigevent notify;
- struct pid* notify_owner;
+ struct pid *notify_owner;
+ u32 notify_self_exec_id;
struct user_namespace *notify_user_ns;
- struct user_struct *user; /* user who created, for accounting */
+ struct ucounts *ucounts; /* user who created, for accounting */
struct sock *notify_sock;
struct sk_buff *notify_cookie;
@@ -85,15 +155,15 @@ struct mqueue_inode_info {
unsigned long qsize; /* size of queue in memory (sum of all msgs) */
};
+static struct file_system_type mqueue_fs_type;
static const struct inode_operations mqueue_dir_inode_operations;
static const struct file_operations mqueue_file_operations;
static const struct super_operations mqueue_super_ops;
+static const struct fs_context_operations mqueue_fs_context_ops;
static void remove_notification(struct mqueue_inode_info *info);
static struct kmem_cache *mqueue_inode_cachep;
-static struct ctl_table_header * mq_sysctl_table;
-
static inline struct mqueue_inode_info *MQUEUE_I(struct inode *inode)
{
return container_of(inode, struct mqueue_inode_info, vfs_inode);
@@ -122,6 +192,7 @@ static int msg_insert(struct msg_msg *msg, struct mqueue_inode_info *info)
{
struct rb_node **p, *parent = NULL;
struct posix_msg_tree_node *leaf;
+ bool rightmost = true;
p = &info->msg_tree.rb_node;
while (*p) {
@@ -130,9 +201,10 @@ static int msg_insert(struct msg_msg *msg, struct mqueue_inode_info *info)
if (likely(leaf->priority == msg->m_type))
goto insert_msg;
- else if (msg->m_type < leaf->priority)
+ else if (msg->m_type < leaf->priority) {
p = &(*p)->rb_left;
- else
+ rightmost = false;
+ } else
p = &(*p)->rb_right;
}
if (info->node_cache) {
@@ -143,9 +215,12 @@ static int msg_insert(struct msg_msg *msg, struct mqueue_inode_info *info)
if (!leaf)
return -ENOMEM;
INIT_LIST_HEAD(&leaf->msg_list);
- info->qsize += sizeof(*leaf);
}
leaf->priority = msg->m_type;
+
+ if (rightmost)
+ info->msg_tree_rightmost = &leaf->rb_node;
+
rb_link_node(&leaf->rb_node, parent, p);
rb_insert_color(&leaf->rb_node, &info->msg_tree);
insert_msg:
@@ -155,23 +230,34 @@ insert_msg:
return 0;
}
+static inline void msg_tree_erase(struct posix_msg_tree_node *leaf,
+ struct mqueue_inode_info *info)
+{
+ struct rb_node *node = &leaf->rb_node;
+
+ if (info->msg_tree_rightmost == node)
+ info->msg_tree_rightmost = rb_prev(node);
+
+ rb_erase(node, &info->msg_tree);
+ if (info->node_cache)
+ kfree(leaf);
+ else
+ info->node_cache = leaf;
+}
+
static inline struct msg_msg *msg_get(struct mqueue_inode_info *info)
{
- struct rb_node **p, *parent = NULL;
+ struct rb_node *parent = NULL;
struct posix_msg_tree_node *leaf;
struct msg_msg *msg;
try_again:
- p = &info->msg_tree.rb_node;
- while (*p) {
- parent = *p;
- /*
- * During insert, low priorities go to the left and high to the
- * right. On receive, we want the highest priorities first, so
- * walk all the way to the right.
- */
- p = &(*p)->rb_right;
- }
+ /*
+ * During insert, low priorities go to the left and high to the
+ * right. On receive, we want the highest priorities first, so
+ * walk all the way to the right.
+ */
+ parent = info->msg_tree_rightmost;
if (!parent) {
if (info->attr.mq_curmsgs) {
pr_warn_once("Inconsistency in POSIX message queue, "
@@ -186,26 +272,14 @@ try_again:
pr_warn_once("Inconsistency in POSIX message queue, "
"empty leaf node but we haven't implemented "
"lazy leaf delete!\n");
- rb_erase(&leaf->rb_node, &info->msg_tree);
- if (info->node_cache) {
- info->qsize -= sizeof(*leaf);
- kfree(leaf);
- } else {
- info->node_cache = leaf;
- }
+ msg_tree_erase(leaf, info);
goto try_again;
} else {
msg = list_first_entry(&leaf->msg_list,
struct msg_msg, m_list);
list_del(&msg->m_list);
if (list_empty(&leaf->msg_list)) {
- rb_erase(&leaf->rb_node, &info->msg_tree);
- if (info->node_cache) {
- info->qsize -= sizeof(*leaf);
- kfree(leaf);
- } else {
- info->node_cache = leaf;
- }
+ msg_tree_erase(leaf, info);
}
}
info->attr.mq_curmsgs--;
@@ -217,7 +291,6 @@ static struct inode *mqueue_get_inode(struct super_block *sb,
struct ipc_namespace *ipc_ns, umode_t mode,
struct mq_attr *attr)
{
- struct user_struct *u = current_user();
struct inode *inode;
int ret = -ENOMEM;
@@ -229,7 +302,7 @@ static struct inode *mqueue_get_inode(struct super_block *sb,
inode->i_mode = mode;
inode->i_uid = current_fsuid();
inode->i_gid = current_fsgid();
- inode->i_mtime = inode->i_ctime = inode->i_atime = CURRENT_TIME;
+ simple_inode_init_ts(inode);
if (S_ISREG(mode)) {
struct mqueue_inode_info *info;
@@ -246,8 +319,9 @@ static struct inode *mqueue_get_inode(struct super_block *sb,
info->notify_owner = NULL;
info->notify_user_ns = NULL;
info->qsize = 0;
- info->user = NULL; /* set when all is ok */
+ info->ucounts = NULL; /* set when all is ok */
info->msg_tree = RB_ROOT;
+ info->msg_tree_rightmost = NULL;
info->node_cache = NULL;
memset(&info->attr, 0, sizeof(info->attr));
info->attr.mq_maxmsg = min(ipc_ns->mq_msg_max,
@@ -271,26 +345,47 @@ static struct inode *mqueue_get_inode(struct super_block *sb,
* that means the min(mq_maxmsg, max_priorities) * struct
* posix_msg_tree_node.
*/
+
+ ret = -EINVAL;
+ if (info->attr.mq_maxmsg <= 0 || info->attr.mq_msgsize <= 0)
+ goto out_inode;
+ if (capable(CAP_SYS_RESOURCE)) {
+ if (info->attr.mq_maxmsg > HARD_MSGMAX ||
+ info->attr.mq_msgsize > HARD_MSGSIZEMAX)
+ goto out_inode;
+ } else {
+ if (info->attr.mq_maxmsg > ipc_ns->mq_msg_max ||
+ info->attr.mq_msgsize > ipc_ns->mq_msgsize_max)
+ goto out_inode;
+ }
+ ret = -EOVERFLOW;
+ /* check for overflow */
+ if (info->attr.mq_msgsize > ULONG_MAX/info->attr.mq_maxmsg)
+ goto out_inode;
mq_treesize = info->attr.mq_maxmsg * sizeof(struct msg_msg) +
min_t(unsigned int, info->attr.mq_maxmsg, MQ_PRIO_MAX) *
sizeof(struct posix_msg_tree_node);
-
- mq_bytes = mq_treesize + (info->attr.mq_maxmsg *
- info->attr.mq_msgsize);
-
- spin_lock(&mq_lock);
- if (u->mq_bytes + mq_bytes < u->mq_bytes ||
- u->mq_bytes + mq_bytes > rlimit(RLIMIT_MSGQUEUE)) {
- spin_unlock(&mq_lock);
- /* mqueue_evict_inode() releases info->messages */
- ret = -EMFILE;
+ mq_bytes = info->attr.mq_maxmsg * info->attr.mq_msgsize;
+ if (mq_bytes + mq_treesize < mq_bytes)
goto out_inode;
+ mq_bytes += mq_treesize;
+ info->ucounts = get_ucounts(current_ucounts());
+ if (info->ucounts) {
+ long msgqueue;
+
+ spin_lock(&mq_lock);
+ msgqueue = inc_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes);
+ if (msgqueue == LONG_MAX || msgqueue > rlimit(RLIMIT_MSGQUEUE)) {
+ dec_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes);
+ spin_unlock(&mq_lock);
+ put_ucounts(info->ucounts);
+ info->ucounts = NULL;
+ /* mqueue_evict_inode() releases info->messages */
+ ret = -EMFILE;
+ goto out_inode;
+ }
+ spin_unlock(&mq_lock);
}
- u->mq_bytes += mq_bytes;
- spin_unlock(&mq_lock);
-
- /* all is ok */
- info->user = get_uid(u);
} else if (S_ISDIR(mode)) {
inc_nlink(inode);
/* Some things misbehave if size == 0 on a directory */
@@ -306,15 +401,17 @@ err:
return ERR_PTR(ret);
}
-static int mqueue_fill_super(struct super_block *sb, void *data, int silent)
+static int mqueue_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct inode *inode;
- struct ipc_namespace *ns = data;
+ struct ipc_namespace *ns = sb->s_fs_info;
- sb->s_blocksize = PAGE_CACHE_SIZE;
- sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+ sb->s_iflags |= SB_I_NOEXEC | SB_I_NODEV;
+ sb->s_blocksize = PAGE_SIZE;
+ sb->s_blocksize_bits = PAGE_SHIFT;
sb->s_magic = MQUEUE_MAGIC;
sb->s_op = &mqueue_super_ops;
+ sb->s_d_flags = DCACHE_DONTCACHE;
inode = mqueue_get_inode(sb, ns, S_IFDIR | S_ISVTX | S_IRWXUGO, NULL);
if (IS_ERR(inode))
@@ -326,26 +423,74 @@ static int mqueue_fill_super(struct super_block *sb, void *data, int silent)
return 0;
}
-static struct dentry *mqueue_mount(struct file_system_type *fs_type,
- int flags, const char *dev_name,
- void *data)
+static int mqueue_get_tree(struct fs_context *fc)
{
- if (!(flags & MS_KERNMOUNT)) {
- struct ipc_namespace *ns = current->nsproxy->ipc_ns;
- /* Don't allow mounting unless the caller has CAP_SYS_ADMIN
- * over the ipc namespace.
- */
- if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
- return ERR_PTR(-EPERM);
+ struct mqueue_fs_context *ctx = fc->fs_private;
- data = ns;
+ /*
+ * With a newly created ipc namespace, we don't need to do a search
+ * for an ipc namespace match, but we still need to set s_fs_info.
+ */
+ if (ctx->newns) {
+ fc->s_fs_info = ctx->ipc_ns;
+ return get_tree_nodev(fc, mqueue_fill_super);
}
- return mount_ns(fs_type, flags, data, mqueue_fill_super);
+ return get_tree_keyed(fc, mqueue_fill_super, ctx->ipc_ns);
+}
+
+static void mqueue_fs_context_free(struct fs_context *fc)
+{
+ struct mqueue_fs_context *ctx = fc->fs_private;
+
+ put_ipc_ns(ctx->ipc_ns);
+ kfree(ctx);
+}
+
+static int mqueue_init_fs_context(struct fs_context *fc)
+{
+ struct mqueue_fs_context *ctx;
+
+ ctx = kzalloc(sizeof(struct mqueue_fs_context), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ ctx->ipc_ns = get_ipc_ns(current->nsproxy->ipc_ns);
+ put_user_ns(fc->user_ns);
+ fc->user_ns = get_user_ns(ctx->ipc_ns->user_ns);
+ fc->fs_private = ctx;
+ fc->ops = &mqueue_fs_context_ops;
+ return 0;
+}
+
+/*
+ * mq_init_ns() is currently the only caller of mq_create_mount().
+ * So the ns parameter is always a newly created ipc namespace.
+ */
+static struct vfsmount *mq_create_mount(struct ipc_namespace *ns)
+{
+ struct mqueue_fs_context *ctx;
+ struct fs_context *fc;
+ struct vfsmount *mnt;
+
+ fc = fs_context_for_mount(&mqueue_fs_type, SB_KERNMOUNT);
+ if (IS_ERR(fc))
+ return ERR_CAST(fc);
+
+ ctx = fc->fs_private;
+ ctx->newns = true;
+ put_ipc_ns(ctx->ipc_ns);
+ ctx->ipc_ns = get_ipc_ns(ns);
+ put_user_ns(fc->user_ns);
+ fc->user_ns = get_user_ns(ctx->ipc_ns->user_ns);
+
+ mnt = fc_mount_longterm(fc);
+ put_fs_context(fc);
+ return mnt;
}
static void init_once(void *foo)
{
- struct mqueue_inode_info *p = (struct mqueue_inode_info *) foo;
+ struct mqueue_inode_info *p = foo;
inode_init_once(&p->vfs_inode);
}
@@ -354,30 +499,23 @@ static struct inode *mqueue_alloc_inode(struct super_block *sb)
{
struct mqueue_inode_info *ei;
- ei = kmem_cache_alloc(mqueue_inode_cachep, GFP_KERNEL);
+ ei = alloc_inode_sb(sb, mqueue_inode_cachep, GFP_KERNEL);
if (!ei)
return NULL;
return &ei->vfs_inode;
}
-static void mqueue_i_callback(struct rcu_head *head)
+static void mqueue_free_inode(struct inode *inode)
{
- struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(mqueue_inode_cachep, MQUEUE_I(inode));
}
-static void mqueue_destroy_inode(struct inode *inode)
-{
- call_rcu(&inode->i_rcu, mqueue_i_callback);
-}
-
static void mqueue_evict_inode(struct inode *inode)
{
struct mqueue_inode_info *info;
- struct user_struct *user;
- unsigned long mq_bytes, mq_treesize;
struct ipc_namespace *ipc_ns;
- struct msg_msg *msg;
+ struct msg_msg *msg, *nmsg;
+ LIST_HEAD(tmp_msg);
clear_inode(inode);
@@ -388,22 +526,28 @@ static void mqueue_evict_inode(struct inode *inode)
info = MQUEUE_I(inode);
spin_lock(&info->lock);
while ((msg = msg_get(info)) != NULL)
- free_msg(msg);
+ list_add_tail(&msg->m_list, &tmp_msg);
kfree(info->node_cache);
spin_unlock(&info->lock);
- /* Total amount of bytes accounted for the mqueue */
- mq_treesize = info->attr.mq_maxmsg * sizeof(struct msg_msg) +
- min_t(unsigned int, info->attr.mq_maxmsg, MQ_PRIO_MAX) *
- sizeof(struct posix_msg_tree_node);
+ list_for_each_entry_safe(msg, nmsg, &tmp_msg, m_list) {
+ list_del(&msg->m_list);
+ free_msg(msg);
+ }
+
+ if (info->ucounts) {
+ unsigned long mq_bytes, mq_treesize;
- mq_bytes = mq_treesize + (info->attr.mq_maxmsg *
- info->attr.mq_msgsize);
+ /* Total amount of bytes accounted for the mqueue */
+ mq_treesize = info->attr.mq_maxmsg * sizeof(struct msg_msg) +
+ min_t(unsigned int, info->attr.mq_maxmsg, MQ_PRIO_MAX) *
+ sizeof(struct posix_msg_tree_node);
+
+ mq_bytes = mq_treesize + (info->attr.mq_maxmsg *
+ info->attr.mq_msgsize);
- user = info->user;
- if (user) {
spin_lock(&mq_lock);
- user->mq_bytes -= mq_bytes;
+ dec_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes);
/*
* get_ns_from_inode() ensures that the
* (ipc_ns = sb->s_fs_info) is either a valid ipc_ns
@@ -413,17 +557,18 @@ static void mqueue_evict_inode(struct inode *inode)
if (ipc_ns)
ipc_ns->mq_queues_count--;
spin_unlock(&mq_lock);
- free_uid(user);
+ put_ucounts(info->ucounts);
+ info->ucounts = NULL;
}
if (ipc_ns)
put_ipc_ns(ipc_ns);
}
-static int mqueue_create(struct inode *dir, struct dentry *dentry,
- umode_t mode, bool excl)
+static int mqueue_create_attr(struct dentry *dentry, umode_t mode, void *arg)
{
+ struct inode *dir = dentry->d_parent->d_inode;
struct inode *inode;
- struct mq_attr *attr = dentry->d_fsdata;
+ struct mq_attr *attr = arg;
int error;
struct ipc_namespace *ipc_ns;
@@ -433,9 +578,9 @@ static int mqueue_create(struct inode *dir, struct dentry *dentry,
error = -EACCES;
goto out_unlock;
}
- if (ipc_ns->mq_queues_count >= HARD_QUEUESMAX ||
- (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
- !capable(CAP_SYS_RESOURCE))) {
+
+ if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max &&
+ !capable(CAP_SYS_RESOURCE)) {
error = -ENOSPC;
goto out_unlock;
}
@@ -452,10 +597,9 @@ static int mqueue_create(struct inode *dir, struct dentry *dentry,
put_ipc_ns(ipc_ns);
dir->i_size += DIRENT_SIZE;
- dir->i_ctime = dir->i_mtime = dir->i_atime = CURRENT_TIME;
+ simple_inode_init_ts(dir);
- d_instantiate(dentry, inode);
- dget(dentry);
+ d_make_persistent(dentry, inode);
return 0;
out_unlock:
spin_unlock(&mq_lock);
@@ -464,15 +608,16 @@ out_unlock:
return error;
}
-static int mqueue_unlink(struct inode *dir, struct dentry *dentry)
+static int mqueue_create(struct mnt_idmap *idmap, struct inode *dir,
+ struct dentry *dentry, umode_t mode, bool excl)
{
- struct inode *inode = dentry->d_inode;
+ return mqueue_create_attr(dentry, mode, NULL);
+}
- dir->i_ctime = dir->i_mtime = dir->i_atime = CURRENT_TIME;
+static int mqueue_unlink(struct inode *dir, struct dentry *dentry)
+{
dir->i_size -= DIRENT_SIZE;
- drop_nlink(inode);
- dput(dentry);
- return 0;
+ return simple_unlink(dir, dentry);
}
/*
@@ -485,7 +630,8 @@ static int mqueue_unlink(struct inode *dir, struct dentry *dentry)
static ssize_t mqueue_read_file(struct file *filp, char __user *u_data,
size_t count, loff_t *off)
{
- struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp));
+ struct inode *inode = file_inode(filp);
+ struct mqueue_inode_info *info = MQUEUE_I(inode);
char buffer[FILENT_SIZE];
ssize_t ret;
@@ -506,7 +652,7 @@ static ssize_t mqueue_read_file(struct file *filp, char __user *u_data,
if (ret <= 0)
return ret;
- file_inode(filp)->i_atime = file_inode(filp)->i_ctime = CURRENT_TIME;
+ inode_set_atime_to_ts(inode, inode_set_ctime_current(inode));
return ret;
}
@@ -522,19 +668,19 @@ static int mqueue_flush_file(struct file *filp, fl_owner_t id)
return 0;
}
-static unsigned int mqueue_poll_file(struct file *filp, struct poll_table_struct *poll_tab)
+static __poll_t mqueue_poll_file(struct file *filp, struct poll_table_struct *poll_tab)
{
struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp));
- int retval = 0;
+ __poll_t retval = 0;
poll_wait(filp, &info->wait_q, poll_tab);
spin_lock(&info->lock);
if (info->attr.mq_curmsgs)
- retval = POLLIN | POLLRDNORM;
+ retval = EPOLLIN | EPOLLRDNORM;
if (info->attr.mq_curmsgs < info->attr.mq_maxmsg)
- retval |= POLLOUT | POLLWRNORM;
+ retval |= EPOLLOUT | EPOLLWRNORM;
spin_unlock(&info->lock);
return retval;
@@ -546,10 +692,8 @@ static void wq_add(struct mqueue_inode_info *info, int sr,
{
struct ext_wait_queue *walk;
- ewp->task = current;
-
list_for_each_entry(walk, &info->e_wait_q[sr].list, list) {
- if (walk->task->static_prio <= current->static_prio) {
+ if (walk->task->prio <= current->prio) {
list_add_tail(&ewp->list, &walk->list);
return;
}
@@ -564,6 +708,7 @@ static void wq_add(struct mqueue_inode_info *info, int sr,
*/
static int wq_sleep(struct mqueue_inode_info *info, int sr,
ktime_t *timeout, struct ext_wait_queue *ewp)
+ __releases(&info->lock)
{
int retval;
signed long time;
@@ -571,21 +716,23 @@ static int wq_sleep(struct mqueue_inode_info *info, int sr,
wq_add(info, sr, ewp);
for (;;) {
- set_current_state(TASK_INTERRUPTIBLE);
+ /* memory barrier not required, we hold info->lock */
+ __set_current_state(TASK_INTERRUPTIBLE);
spin_unlock(&info->lock);
time = schedule_hrtimeout_range_clock(timeout, 0,
HRTIMER_MODE_ABS, CLOCK_REALTIME);
- while (ewp->state == STATE_PENDING)
- cpu_relax();
-
- if (ewp->state == STATE_READY) {
+ if (READ_ONCE(ewp->state) == STATE_READY) {
+ /* see MQ_BARRIER for purpose/pairing */
+ smp_acquire__after_ctrl_dep();
retval = 0;
goto out;
}
spin_lock(&info->lock);
- if (ewp->state == STATE_READY) {
+
+ /* we hold info->lock, so no memory barrier required */
+ if (READ_ONCE(ewp->state) == STATE_READY) {
retval = 0;
goto out_unlock;
}
@@ -622,7 +769,7 @@ static struct ext_wait_queue *wq_get_first_waiter(
static inline void set_cookie(struct sk_buff *skb, char code)
{
- ((char*)skb->data)[NOTIFY_COOKIE_LEN-1] = code;
+ ((char *)skb->data)[NOTIFY_COOKIE_LEN-1] = code;
}
/*
@@ -637,27 +784,44 @@ static void __do_notify(struct mqueue_inode_info *info)
* synchronously. */
if (info->notify_owner &&
info->attr.mq_curmsgs == 1) {
- struct siginfo sig_i;
switch (info->notify.sigev_notify) {
case SIGEV_NONE:
break;
- case SIGEV_SIGNAL:
- /* sends signal */
+ case SIGEV_SIGNAL: {
+ struct kernel_siginfo sig_i;
+ struct task_struct *task;
+
+ /* do_mq_notify() accepts sigev_signo == 0, why?? */
+ if (!info->notify.sigev_signo)
+ break;
+ clear_siginfo(&sig_i);
sig_i.si_signo = info->notify.sigev_signo;
sig_i.si_errno = 0;
sig_i.si_code = SI_MESGQ;
sig_i.si_value = info->notify.sigev_value;
- /* map current pid/uid into info->owner's namespaces */
rcu_read_lock();
+ /* map current pid/uid into info->owner's namespaces */
sig_i.si_pid = task_tgid_nr_ns(current,
ns_of_pid(info->notify_owner));
- sig_i.si_uid = from_kuid_munged(info->notify_user_ns, current_uid());
+ sig_i.si_uid = from_kuid_munged(info->notify_user_ns,
+ current_uid());
+ /*
+ * We can't use kill_pid_info(), this signal should
+ * bypass check_kill_permission(). It is from kernel
+ * but si_fromuser() can't know this.
+ * We do check the self_exec_id, to avoid sending
+ * signals to programs that don't expect them.
+ */
+ task = pid_task(info->notify_owner, PIDTYPE_TGID);
+ if (task && task->self_exec_id ==
+ info->notify_self_exec_id) {
+ do_send_sig_info(info->notify.sigev_signo,
+ &sig_i, task, PIDTYPE_TGID);
+ }
rcu_read_unlock();
-
- kill_pid_info(info->notify.sigev_signo,
- &sig_i, info->notify_owner);
break;
+ }
case SIGEV_THREAD:
set_cookie(info->notify_cookie, NOTIFY_WOKENUP);
netlink_sendskb(info->notify_sock, info->notify_cookie);
@@ -672,15 +836,13 @@ static void __do_notify(struct mqueue_inode_info *info)
wake_up(&info->wait_q);
}
-static int prepare_timeout(const struct timespec __user *u_abs_timeout,
- ktime_t *expires, struct timespec *ts)
+static int prepare_timeout(const struct __kernel_timespec __user *u_abs_timeout,
+ struct timespec64 *ts)
{
- if (copy_from_user(ts, u_abs_timeout, sizeof(struct timespec)))
+ if (get_timespec64(ts, u_abs_timeout))
return -EFAULT;
- if (!timespec_valid(ts))
+ if (!timespec64_valid(ts))
return -EINVAL;
-
- *expires = timespec_to_ktime(*ts);
return 0;
}
@@ -697,163 +859,84 @@ static void remove_notification(struct mqueue_inode_info *info)
info->notify_user_ns = NULL;
}
-static int mq_attr_ok(struct ipc_namespace *ipc_ns, struct mq_attr *attr)
+static int prepare_open(struct dentry *dentry, int oflag, int ro,
+ umode_t mode, struct filename *name,
+ struct mq_attr *attr)
{
- int mq_treesize;
- unsigned long total_size;
+ static const int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE,
+ MAY_READ | MAY_WRITE };
+ int acc;
- if (attr->mq_maxmsg <= 0 || attr->mq_msgsize <= 0)
- return -EINVAL;
- if (capable(CAP_SYS_RESOURCE)) {
- if (attr->mq_maxmsg > HARD_MSGMAX ||
- attr->mq_msgsize > HARD_MSGSIZEMAX)
- return -EINVAL;
- } else {
- if (attr->mq_maxmsg > ipc_ns->mq_msg_max ||
- attr->mq_msgsize > ipc_ns->mq_msgsize_max)
- return -EINVAL;
+ if (d_really_is_negative(dentry)) {
+ if (!(oflag & O_CREAT))
+ return -ENOENT;
+ if (ro)
+ return ro;
+ audit_inode_parent_hidden(name, dentry->d_parent);
+ return vfs_mkobj(dentry, mode & ~current_umask(),
+ mqueue_create_attr, attr);
}
- /* check for overflow */
- if (attr->mq_msgsize > ULONG_MAX/attr->mq_maxmsg)
- return -EOVERFLOW;
- mq_treesize = attr->mq_maxmsg * sizeof(struct msg_msg) +
- min_t(unsigned int, attr->mq_maxmsg, MQ_PRIO_MAX) *
- sizeof(struct posix_msg_tree_node);
- total_size = attr->mq_maxmsg * attr->mq_msgsize;
- if (total_size + mq_treesize < total_size)
- return -EOVERFLOW;
- return 0;
+ /* it already existed */
+ audit_inode(name, dentry, 0);
+ if ((oflag & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL))
+ return -EEXIST;
+ if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY))
+ return -EINVAL;
+ acc = oflag2acc[oflag & O_ACCMODE];
+ return inode_permission(&nop_mnt_idmap, d_inode(dentry), acc);
}
-/*
- * Invoked when creating a new queue via sys_mq_open
- */
-static struct file *do_create(struct ipc_namespace *ipc_ns, struct inode *dir,
- struct path *path, int oflag, umode_t mode,
- struct mq_attr *attr)
+static struct file *mqueue_file_open(struct filename *name,
+ struct vfsmount *mnt, int oflag, int ro,
+ umode_t mode, struct mq_attr *attr)
{
- const struct cred *cred = current_cred();
+ struct dentry *dentry;
+ struct file *file;
int ret;
- if (attr) {
- ret = mq_attr_ok(ipc_ns, attr);
- if (ret)
- return ERR_PTR(ret);
- /* store for use during create */
- path->dentry->d_fsdata = attr;
- } else {
- struct mq_attr def_attr;
-
- def_attr.mq_maxmsg = min(ipc_ns->mq_msg_max,
- ipc_ns->mq_msg_default);
- def_attr.mq_msgsize = min(ipc_ns->mq_msgsize_max,
- ipc_ns->mq_msgsize_default);
- ret = mq_attr_ok(ipc_ns, &def_attr);
- if (ret)
- return ERR_PTR(ret);
+ dentry = start_creating_noperm(mnt->mnt_root, &QSTR(name->name));
+ if (IS_ERR(dentry))
+ return ERR_CAST(dentry);
+
+ ret = prepare_open(dentry, oflag, ro, mode, name, attr);
+ file = ERR_PTR(ret);
+ if (!ret) {
+ const struct path path = { .mnt = mnt, .dentry = dentry };
+ file = dentry_open(&path, oflag, current_cred());
}
- mode &= ~current_umask();
- ret = vfs_create(dir, path->dentry, mode, true);
- path->dentry->d_fsdata = NULL;
- if (ret)
- return ERR_PTR(ret);
- return dentry_open(path, oflag, cred);
+ end_creating(dentry);
+ return file;
}
-/* Opens existing queue */
-static struct file *do_open(struct path *path, int oflag)
+static int do_mq_open(const char __user *u_name, int oflag, umode_t mode,
+ struct mq_attr *attr)
{
- static const int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE,
- MAY_READ | MAY_WRITE };
- int acc;
- if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY))
- return ERR_PTR(-EINVAL);
- acc = oflag2acc[oflag & O_ACCMODE];
- if (inode_permission(path->dentry->d_inode, acc))
- return ERR_PTR(-EACCES);
- return dentry_open(path, oflag, current_cred());
+ struct filename *name __free(putname) = NULL;;
+ struct vfsmount *mnt = current->nsproxy->ipc_ns->mq_mnt;
+ int fd, ro;
+
+ audit_mq_open(oflag, mode, attr);
+
+ name = getname(u_name);
+ if (IS_ERR(name))
+ return PTR_ERR(name);
+
+ ro = mnt_want_write(mnt); /* we'll drop it in any case */
+ fd = FD_ADD(O_CLOEXEC, mqueue_file_open(name, mnt, oflag, ro, mode, attr));
+ if (!ro)
+ mnt_drop_write(mnt);
+ return fd;
}
SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode,
struct mq_attr __user *, u_attr)
{
- struct path path;
- struct file *filp;
- struct filename *name;
struct mq_attr attr;
- int fd, error;
- struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
- struct vfsmount *mnt = ipc_ns->mq_mnt;
- struct dentry *root = mnt->mnt_root;
- int ro;
-
if (u_attr && copy_from_user(&attr, u_attr, sizeof(struct mq_attr)))
return -EFAULT;
- audit_mq_open(oflag, mode, u_attr ? &attr : NULL);
-
- if (IS_ERR(name = getname(u_name)))
- return PTR_ERR(name);
-
- fd = get_unused_fd_flags(O_CLOEXEC);
- if (fd < 0)
- goto out_putname;
-
- ro = mnt_want_write(mnt); /* we'll drop it in any case */
- error = 0;
- mutex_lock(&root->d_inode->i_mutex);
- path.dentry = lookup_one_len(name->name, root, strlen(name->name));
- if (IS_ERR(path.dentry)) {
- error = PTR_ERR(path.dentry);
- goto out_putfd;
- }
- path.mnt = mntget(mnt);
-
- if (oflag & O_CREAT) {
- if (path.dentry->d_inode) { /* entry already exists */
- audit_inode(name, path.dentry, 0);
- if (oflag & O_EXCL) {
- error = -EEXIST;
- goto out;
- }
- filp = do_open(&path, oflag);
- } else {
- if (ro) {
- error = ro;
- goto out;
- }
- audit_inode_parent_hidden(name, root);
- filp = do_create(ipc_ns, root->d_inode,
- &path, oflag, mode,
- u_attr ? &attr : NULL);
- }
- } else {
- if (!path.dentry->d_inode) {
- error = -ENOENT;
- goto out;
- }
- audit_inode(name, path.dentry, 0);
- filp = do_open(&path, oflag);
- }
-
- if (!IS_ERR(filp))
- fd_install(fd, filp);
- else
- error = PTR_ERR(filp);
-out:
- path_put(&path);
-out_putfd:
- if (error) {
- put_unused_fd(fd);
- fd = error;
- }
- mutex_unlock(&root->d_inode->i_mutex);
- if (!ro)
- mnt_drop_write(mnt);
-out_putname:
- putname(name);
- return fd;
+ return do_mq_open(u_name, oflag, mode, u_attr ? &attr : NULL);
}
SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
@@ -861,7 +944,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
int err;
struct filename *name;
struct dentry *dentry;
- struct inode *inode = NULL;
+ struct inode *inode;
struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
struct vfsmount *mnt = ipc_ns->mq_mnt;
@@ -873,27 +956,20 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
err = mnt_want_write(mnt);
if (err)
goto out_name;
- mutex_lock_nested(&mnt->mnt_root->d_inode->i_mutex, I_MUTEX_PARENT);
- dentry = lookup_one_len(name->name, mnt->mnt_root,
- strlen(name->name));
+ dentry = start_removing_noperm(mnt->mnt_root, &QSTR(name->name));
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
- goto out_unlock;
+ goto out_drop_write;
}
- inode = dentry->d_inode;
- if (!inode) {
- err = -ENOENT;
- } else {
- ihold(inode);
- err = vfs_unlink(dentry->d_parent->d_inode, dentry);
- }
- dput(dentry);
+ inode = d_inode(dentry);
+ ihold(inode);
+ err = vfs_unlink(&nop_mnt_idmap, d_inode(mnt->mnt_root),
+ dentry, NULL);
+ end_removing(dentry);
+ iput(inode);
-out_unlock:
- mutex_unlock(&mnt->mnt_root->d_inode->i_mutex);
- if (inode)
- iput(inode);
+out_drop_write:
mnt_drop_write(mnt);
out_name:
putname(name);
@@ -907,33 +983,49 @@ out_name:
* list of waiting receivers. A sender checks that list before adding the new
* message into the message array. If there is a waiting receiver, then it
* bypasses the message array and directly hands the message over to the
- * receiver.
- * The receiver accepts the message and returns without grabbing the queue
- * spinlock. Therefore an intermediate STATE_PENDING state and memory barriers
- * are necessary. The same algorithm is used for sysv semaphores, see
- * ipc/sem.c for more details.
+ * receiver. The receiver accepts the message and returns without grabbing the
+ * queue spinlock:
+ *
+ * - Set pointer to message.
+ * - Queue the receiver task for later wakeup (without the info->lock).
+ * - Update its state to STATE_READY. Now the receiver can continue.
+ * - Wake up the process after the lock is dropped. Should the process wake up
+ * before this wakeup (due to a timeout or a signal) it will either see
+ * STATE_READY and continue or acquire the lock to check the state again.
*
* The same algorithm is used for senders.
*/
+static inline void __pipelined_op(struct wake_q_head *wake_q,
+ struct mqueue_inode_info *info,
+ struct ext_wait_queue *this)
+{
+ struct task_struct *task;
+
+ list_del(&this->list);
+ task = get_task_struct(this->task);
+
+ /* see MQ_BARRIER for purpose/pairing */
+ smp_store_release(&this->state, STATE_READY);
+ wake_q_add_safe(wake_q, task);
+}
+
/* pipelined_send() - send a message directly to the task waiting in
* sys_mq_timedreceive() (without inserting message into a queue).
*/
-static inline void pipelined_send(struct mqueue_inode_info *info,
+static inline void pipelined_send(struct wake_q_head *wake_q,
+ struct mqueue_inode_info *info,
struct msg_msg *message,
struct ext_wait_queue *receiver)
{
receiver->msg = message;
- list_del(&receiver->list);
- receiver->state = STATE_PENDING;
- wake_up_process(receiver->task);
- smp_wmb();
- receiver->state = STATE_READY;
+ __pipelined_op(wake_q, info, receiver);
}
/* pipelined_receive() - if there is task waiting in sys_mq_timedsend()
* gets its message and put to the queue (we have one free place for sure). */
-static inline void pipelined_receive(struct mqueue_inode_info *info)
+static inline void pipelined_receive(struct wake_q_head *wake_q,
+ struct mqueue_inode_info *info)
{
struct ext_wait_queue *sender = wq_get_first_waiter(info, SEND);
@@ -944,71 +1036,55 @@ static inline void pipelined_receive(struct mqueue_inode_info *info)
}
if (msg_insert(sender->msg, info))
return;
- list_del(&sender->list);
- sender->state = STATE_PENDING;
- wake_up_process(sender->task);
- smp_wmb();
- sender->state = STATE_READY;
+
+ __pipelined_op(wake_q, info, sender);
}
-SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
- size_t, msg_len, unsigned int, msg_prio,
- const struct timespec __user *, u_abs_timeout)
+static int do_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr,
+ size_t msg_len, unsigned int msg_prio,
+ struct timespec64 *ts)
{
- struct fd f;
struct inode *inode;
struct ext_wait_queue wait;
struct ext_wait_queue *receiver;
struct msg_msg *msg_ptr;
struct mqueue_inode_info *info;
ktime_t expires, *timeout = NULL;
- struct timespec ts;
struct posix_msg_tree_node *new_leaf = NULL;
int ret = 0;
-
- if (u_abs_timeout) {
- int res = prepare_timeout(u_abs_timeout, &expires, &ts);
- if (res)
- return res;
- timeout = &expires;
- }
+ DEFINE_WAKE_Q(wake_q);
if (unlikely(msg_prio >= (unsigned long) MQ_PRIO_MAX))
return -EINVAL;
- audit_mq_sendrecv(mqdes, msg_len, msg_prio, timeout ? &ts : NULL);
-
- f = fdget(mqdes);
- if (unlikely(!f.file)) {
- ret = -EBADF;
- goto out;
+ if (ts) {
+ expires = timespec64_to_ktime(*ts);
+ timeout = &expires;
}
- inode = file_inode(f.file);
- if (unlikely(f.file->f_op != &mqueue_file_operations)) {
- ret = -EBADF;
- goto out_fput;
- }
+ audit_mq_sendrecv(mqdes, msg_len, msg_prio, ts);
+
+ CLASS(fd, f)(mqdes);
+ if (fd_empty(f))
+ return -EBADF;
+
+ inode = file_inode(fd_file(f));
+ if (unlikely(fd_file(f)->f_op != &mqueue_file_operations))
+ return -EBADF;
info = MQUEUE_I(inode);
- audit_inode(NULL, f.file->f_path.dentry, 0);
+ audit_file(fd_file(f));
- if (unlikely(!(f.file->f_mode & FMODE_WRITE))) {
- ret = -EBADF;
- goto out_fput;
- }
+ if (unlikely(!(fd_file(f)->f_mode & FMODE_WRITE)))
+ return -EBADF;
- if (unlikely(msg_len > info->attr.mq_msgsize)) {
- ret = -EMSGSIZE;
- goto out_fput;
- }
+ if (unlikely(msg_len > info->attr.mq_msgsize))
+ return -EMSGSIZE;
/* First try to allocate memory, before doing anything with
* existing queues. */
msg_ptr = load_msg(u_msg_ptr, msg_len);
- if (IS_ERR(msg_ptr)) {
- ret = PTR_ERR(msg_ptr);
- goto out_fput;
- }
+ if (IS_ERR(msg_ptr))
+ return PTR_ERR(msg_ptr);
msg_ptr->m_ts = msg_len;
msg_ptr->m_type = msg_prio;
@@ -1026,19 +1102,20 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
/* Save our speculative allocation into the cache */
INIT_LIST_HEAD(&new_leaf->msg_list);
info->node_cache = new_leaf;
- info->qsize += sizeof(*new_leaf);
new_leaf = NULL;
} else {
kfree(new_leaf);
}
if (info->attr.mq_curmsgs == info->attr.mq_maxmsg) {
- if (f.file->f_flags & O_NONBLOCK) {
+ if (fd_file(f)->f_flags & O_NONBLOCK) {
ret = -EAGAIN;
} else {
wait.task = current;
wait.msg = (void *) msg_ptr;
- wait.state = STATE_NONE;
+
+ /* memory barrier not required, we hold info->lock */
+ WRITE_ONCE(wait.state, STATE_NONE);
ret = wq_sleep(info, SEND, timeout, &wait);
/*
* wq_sleep must be called with info->lock held, and
@@ -1049,7 +1126,7 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
} else {
receiver = wq_get_first_waiter(info, RECV);
if (receiver) {
- pipelined_send(info, msg_ptr, receiver);
+ pipelined_send(&wake_q, info, msg_ptr, receiver);
} else {
/* adds message to the queue */
ret = msg_insert(msg_ptr, info);
@@ -1057,67 +1134,52 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
goto out_unlock;
__do_notify(info);
}
- inode->i_atime = inode->i_mtime = inode->i_ctime =
- CURRENT_TIME;
+ simple_inode_init_ts(inode);
}
out_unlock:
spin_unlock(&info->lock);
+ wake_up_q(&wake_q);
out_free:
if (ret)
free_msg(msg_ptr);
-out_fput:
- fdput(f);
-out:
return ret;
}
-SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr,
- size_t, msg_len, unsigned int __user *, u_msg_prio,
- const struct timespec __user *, u_abs_timeout)
+static int do_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr,
+ size_t msg_len, unsigned int __user *u_msg_prio,
+ struct timespec64 *ts)
{
ssize_t ret;
struct msg_msg *msg_ptr;
- struct fd f;
struct inode *inode;
struct mqueue_inode_info *info;
struct ext_wait_queue wait;
ktime_t expires, *timeout = NULL;
- struct timespec ts;
struct posix_msg_tree_node *new_leaf = NULL;
- if (u_abs_timeout) {
- int res = prepare_timeout(u_abs_timeout, &expires, &ts);
- if (res)
- return res;
+ if (ts) {
+ expires = timespec64_to_ktime(*ts);
timeout = &expires;
}
- audit_mq_sendrecv(mqdes, msg_len, 0, timeout ? &ts : NULL);
+ audit_mq_sendrecv(mqdes, msg_len, 0, ts);
- f = fdget(mqdes);
- if (unlikely(!f.file)) {
- ret = -EBADF;
- goto out;
- }
+ CLASS(fd, f)(mqdes);
+ if (fd_empty(f))
+ return -EBADF;
- inode = file_inode(f.file);
- if (unlikely(f.file->f_op != &mqueue_file_operations)) {
- ret = -EBADF;
- goto out_fput;
- }
+ inode = file_inode(fd_file(f));
+ if (unlikely(fd_file(f)->f_op != &mqueue_file_operations))
+ return -EBADF;
info = MQUEUE_I(inode);
- audit_inode(NULL, f.file->f_path.dentry, 0);
+ audit_file(fd_file(f));
- if (unlikely(!(f.file->f_mode & FMODE_READ))) {
- ret = -EBADF;
- goto out_fput;
- }
+ if (unlikely(!(fd_file(f)->f_mode & FMODE_READ)))
+ return -EBADF;
/* checks if buffer is big enough */
- if (unlikely(msg_len < info->attr.mq_msgsize)) {
- ret = -EMSGSIZE;
- goto out_fput;
- }
+ if (unlikely(msg_len < info->attr.mq_msgsize))
+ return -EMSGSIZE;
/*
* msg_insert really wants us to have a valid, spare node struct so
@@ -1133,30 +1195,33 @@ SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr,
/* Save our speculative allocation into the cache */
INIT_LIST_HEAD(&new_leaf->msg_list);
info->node_cache = new_leaf;
- info->qsize += sizeof(*new_leaf);
} else {
kfree(new_leaf);
}
if (info->attr.mq_curmsgs == 0) {
- if (f.file->f_flags & O_NONBLOCK) {
+ if (fd_file(f)->f_flags & O_NONBLOCK) {
spin_unlock(&info->lock);
ret = -EAGAIN;
} else {
wait.task = current;
- wait.state = STATE_NONE;
+
+ /* memory barrier not required, we hold info->lock */
+ WRITE_ONCE(wait.state, STATE_NONE);
ret = wq_sleep(info, RECV, timeout, &wait);
msg_ptr = wait.msg;
}
} else {
+ DEFINE_WAKE_Q(wake_q);
+
msg_ptr = msg_get(info);
- inode->i_atime = inode->i_mtime = inode->i_ctime =
- CURRENT_TIME;
+ simple_inode_init_ts(inode);
/* There is now free space in queue. */
- pipelined_receive(info);
+ pipelined_receive(&wake_q, info);
spin_unlock(&info->lock);
+ wake_up_q(&wake_q);
ret = 0;
}
if (ret == 0) {
@@ -1168,116 +1233,122 @@ SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr,
}
free_msg(msg_ptr);
}
-out_fput:
- fdput(f);
-out:
return ret;
}
+SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
+ size_t, msg_len, unsigned int, msg_prio,
+ const struct __kernel_timespec __user *, u_abs_timeout)
+{
+ struct timespec64 ts, *p = NULL;
+ if (u_abs_timeout) {
+ int res = prepare_timeout(u_abs_timeout, &ts);
+ if (res)
+ return res;
+ p = &ts;
+ }
+ return do_mq_timedsend(mqdes, u_msg_ptr, msg_len, msg_prio, p);
+}
+
+SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr,
+ size_t, msg_len, unsigned int __user *, u_msg_prio,
+ const struct __kernel_timespec __user *, u_abs_timeout)
+{
+ struct timespec64 ts, *p = NULL;
+ if (u_abs_timeout) {
+ int res = prepare_timeout(u_abs_timeout, &ts);
+ if (res)
+ return res;
+ p = &ts;
+ }
+ return do_mq_timedreceive(mqdes, u_msg_ptr, msg_len, u_msg_prio, p);
+}
+
/*
* Notes: the case when user wants us to deregister (with NULL as pointer)
* and he isn't currently owner of notification, will be silently discarded.
* It isn't explicitly defined in the POSIX.
*/
-SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
- const struct sigevent __user *, u_notification)
+static int do_mq_notify(mqd_t mqdes, const struct sigevent *notification)
{
int ret;
- struct fd f;
struct sock *sock;
struct inode *inode;
- struct sigevent notification;
struct mqueue_inode_info *info;
struct sk_buff *nc;
- if (u_notification) {
- if (copy_from_user(&notification, u_notification,
- sizeof(struct sigevent)))
- return -EFAULT;
- }
-
- audit_mq_notify(mqdes, u_notification ? &notification : NULL);
+ audit_mq_notify(mqdes, notification);
nc = NULL;
sock = NULL;
- if (u_notification != NULL) {
- if (unlikely(notification.sigev_notify != SIGEV_NONE &&
- notification.sigev_notify != SIGEV_SIGNAL &&
- notification.sigev_notify != SIGEV_THREAD))
+ if (notification != NULL) {
+ if (unlikely(notification->sigev_notify != SIGEV_NONE &&
+ notification->sigev_notify != SIGEV_SIGNAL &&
+ notification->sigev_notify != SIGEV_THREAD))
return -EINVAL;
- if (notification.sigev_notify == SIGEV_SIGNAL &&
- !valid_signal(notification.sigev_signo)) {
+ if (notification->sigev_notify == SIGEV_SIGNAL &&
+ !valid_signal(notification->sigev_signo)) {
return -EINVAL;
}
- if (notification.sigev_notify == SIGEV_THREAD) {
+ if (notification->sigev_notify == SIGEV_THREAD) {
long timeo;
/* create the notify skb */
nc = alloc_skb(NOTIFY_COOKIE_LEN, GFP_KERNEL);
- if (!nc) {
- ret = -ENOMEM;
- goto out;
- }
+ if (!nc)
+ return -ENOMEM;
+
if (copy_from_user(nc->data,
- notification.sigev_value.sival_ptr,
+ notification->sigev_value.sival_ptr,
NOTIFY_COOKIE_LEN)) {
- ret = -EFAULT;
- goto out;
+ kfree_skb(nc);
+ return -EFAULT;
}
/* TODO: add a header? */
skb_put(nc, NOTIFY_COOKIE_LEN);
/* and attach it to the socket */
retry:
- f = fdget(notification.sigev_signo);
- if (!f.file) {
- ret = -EBADF;
- goto out;
- }
- sock = netlink_getsockbyfilp(f.file);
- fdput(f);
+ sock = netlink_getsockbyfd(notification->sigev_signo);
if (IS_ERR(sock)) {
- ret = PTR_ERR(sock);
- sock = NULL;
- goto out;
+ kfree_skb(nc);
+ return PTR_ERR(sock);
}
timeo = MAX_SCHEDULE_TIMEOUT;
ret = netlink_attachskb(sock, nc, &timeo, NULL);
if (ret == 1)
goto retry;
- if (ret) {
- sock = NULL;
- nc = NULL;
- goto out;
- }
+ if (ret)
+ return ret;
}
}
- f = fdget(mqdes);
- if (!f.file) {
+ CLASS(fd, f)(mqdes);
+ if (fd_empty(f)) {
ret = -EBADF;
goto out;
}
- inode = file_inode(f.file);
- if (unlikely(f.file->f_op != &mqueue_file_operations)) {
+ inode = file_inode(fd_file(f));
+ if (unlikely(fd_file(f)->f_op != &mqueue_file_operations)) {
ret = -EBADF;
- goto out_fput;
+ goto out;
}
info = MQUEUE_I(inode);
ret = 0;
spin_lock(&info->lock);
- if (u_notification == NULL) {
+ if (notification == NULL) {
if (info->notify_owner == task_tgid(current)) {
remove_notification(info);
- inode->i_atime = inode->i_ctime = CURRENT_TIME;
+ inode_set_atime_to_ts(inode,
+ inode_set_ctime_current(inode));
}
} else if (info->notify_owner != NULL) {
ret = -EBUSY;
} else {
- switch (notification.sigev_notify) {
+ switch (notification->sigev_notify) {
case SIGEV_NONE:
info->notify.sigev_notify = SIGEV_NONE;
break;
@@ -1289,87 +1360,237 @@ retry:
info->notify.sigev_notify = SIGEV_THREAD;
break;
case SIGEV_SIGNAL:
- info->notify.sigev_signo = notification.sigev_signo;
- info->notify.sigev_value = notification.sigev_value;
+ info->notify.sigev_signo = notification->sigev_signo;
+ info->notify.sigev_value = notification->sigev_value;
info->notify.sigev_notify = SIGEV_SIGNAL;
+ info->notify_self_exec_id = current->self_exec_id;
break;
}
info->notify_owner = get_pid(task_tgid(current));
info->notify_user_ns = get_user_ns(current_user_ns());
- inode->i_atime = inode->i_ctime = CURRENT_TIME;
+ inode_set_atime_to_ts(inode, inode_set_ctime_current(inode));
}
spin_unlock(&info->lock);
-out_fput:
- fdput(f);
out:
- if (sock) {
+ if (sock)
netlink_detachskb(sock, nc);
- } else if (nc) {
- dev_kfree_skb(nc);
- }
return ret;
}
+SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
+ const struct sigevent __user *, u_notification)
+{
+ struct sigevent n, *p = NULL;
+ if (u_notification) {
+ if (copy_from_user(&n, u_notification, sizeof(struct sigevent)))
+ return -EFAULT;
+ p = &n;
+ }
+ return do_mq_notify(mqdes, p);
+}
+
+static int do_mq_getsetattr(int mqdes, struct mq_attr *new, struct mq_attr *old)
+{
+ struct inode *inode;
+ struct mqueue_inode_info *info;
+
+ if (new && (new->mq_flags & (~O_NONBLOCK)))
+ return -EINVAL;
+
+ CLASS(fd, f)(mqdes);
+ if (fd_empty(f))
+ return -EBADF;
+
+ if (unlikely(fd_file(f)->f_op != &mqueue_file_operations))
+ return -EBADF;
+
+ inode = file_inode(fd_file(f));
+ info = MQUEUE_I(inode);
+
+ spin_lock(&info->lock);
+
+ if (old) {
+ *old = info->attr;
+ old->mq_flags = fd_file(f)->f_flags & O_NONBLOCK;
+ }
+ if (new) {
+ audit_mq_getsetattr(mqdes, new);
+ spin_lock(&fd_file(f)->f_lock);
+ if (new->mq_flags & O_NONBLOCK)
+ fd_file(f)->f_flags |= O_NONBLOCK;
+ else
+ fd_file(f)->f_flags &= ~O_NONBLOCK;
+ spin_unlock(&fd_file(f)->f_lock);
+
+ inode_set_atime_to_ts(inode, inode_set_ctime_current(inode));
+ }
+
+ spin_unlock(&info->lock);
+ return 0;
+}
+
SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes,
const struct mq_attr __user *, u_mqstat,
struct mq_attr __user *, u_omqstat)
{
int ret;
struct mq_attr mqstat, omqstat;
- struct fd f;
- struct inode *inode;
- struct mqueue_inode_info *info;
+ struct mq_attr *new = NULL, *old = NULL;
- if (u_mqstat != NULL) {
- if (copy_from_user(&mqstat, u_mqstat, sizeof(struct mq_attr)))
+ if (u_mqstat) {
+ new = &mqstat;
+ if (copy_from_user(new, u_mqstat, sizeof(struct mq_attr)))
return -EFAULT;
- if (mqstat.mq_flags & (~O_NONBLOCK))
- return -EINVAL;
}
+ if (u_omqstat)
+ old = &omqstat;
- f = fdget(mqdes);
- if (!f.file) {
- ret = -EBADF;
- goto out;
+ ret = do_mq_getsetattr(mqdes, new, old);
+ if (ret || !old)
+ return ret;
+
+ if (copy_to_user(u_omqstat, old, sizeof(struct mq_attr)))
+ return -EFAULT;
+ return 0;
+}
+
+#ifdef CONFIG_COMPAT
+
+struct compat_mq_attr {
+ compat_long_t mq_flags; /* message queue flags */
+ compat_long_t mq_maxmsg; /* maximum number of messages */
+ compat_long_t mq_msgsize; /* maximum message size */
+ compat_long_t mq_curmsgs; /* number of messages currently queued */
+ compat_long_t __reserved[4]; /* ignored for input, zeroed for output */
+};
+
+static inline int get_compat_mq_attr(struct mq_attr *attr,
+ const struct compat_mq_attr __user *uattr)
+{
+ struct compat_mq_attr v;
+
+ if (copy_from_user(&v, uattr, sizeof(*uattr)))
+ return -EFAULT;
+
+ memset(attr, 0, sizeof(*attr));
+ attr->mq_flags = v.mq_flags;
+ attr->mq_maxmsg = v.mq_maxmsg;
+ attr->mq_msgsize = v.mq_msgsize;
+ attr->mq_curmsgs = v.mq_curmsgs;
+ return 0;
+}
+
+static inline int put_compat_mq_attr(const struct mq_attr *attr,
+ struct compat_mq_attr __user *uattr)
+{
+ struct compat_mq_attr v;
+
+ memset(&v, 0, sizeof(v));
+ v.mq_flags = attr->mq_flags;
+ v.mq_maxmsg = attr->mq_maxmsg;
+ v.mq_msgsize = attr->mq_msgsize;
+ v.mq_curmsgs = attr->mq_curmsgs;
+ if (copy_to_user(uattr, &v, sizeof(*uattr)))
+ return -EFAULT;
+ return 0;
+}
+
+COMPAT_SYSCALL_DEFINE4(mq_open, const char __user *, u_name,
+ int, oflag, compat_mode_t, mode,
+ struct compat_mq_attr __user *, u_attr)
+{
+ struct mq_attr attr, *p = NULL;
+ if (u_attr && oflag & O_CREAT) {
+ p = &attr;
+ if (get_compat_mq_attr(&attr, u_attr))
+ return -EFAULT;
}
+ return do_mq_open(u_name, oflag, mode, p);
+}
- inode = file_inode(f.file);
- if (unlikely(f.file->f_op != &mqueue_file_operations)) {
- ret = -EBADF;
- goto out_fput;
+COMPAT_SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes,
+ const struct compat_sigevent __user *, u_notification)
+{
+ struct sigevent n, *p = NULL;
+ if (u_notification) {
+ if (get_compat_sigevent(&n, u_notification))
+ return -EFAULT;
+ if (n.sigev_notify == SIGEV_THREAD)
+ n.sigev_value.sival_ptr = compat_ptr(n.sigev_value.sival_int);
+ p = &n;
}
- info = MQUEUE_I(inode);
+ return do_mq_notify(mqdes, p);
+}
- spin_lock(&info->lock);
+COMPAT_SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes,
+ const struct compat_mq_attr __user *, u_mqstat,
+ struct compat_mq_attr __user *, u_omqstat)
+{
+ int ret;
+ struct mq_attr mqstat, omqstat;
+ struct mq_attr *new = NULL, *old = NULL;
- omqstat = info->attr;
- omqstat.mq_flags = f.file->f_flags & O_NONBLOCK;
if (u_mqstat) {
- audit_mq_getsetattr(mqdes, &mqstat);
- spin_lock(&f.file->f_lock);
- if (mqstat.mq_flags & O_NONBLOCK)
- f.file->f_flags |= O_NONBLOCK;
- else
- f.file->f_flags &= ~O_NONBLOCK;
- spin_unlock(&f.file->f_lock);
-
- inode->i_atime = inode->i_ctime = CURRENT_TIME;
+ new = &mqstat;
+ if (get_compat_mq_attr(new, u_mqstat))
+ return -EFAULT;
}
+ if (u_omqstat)
+ old = &omqstat;
- spin_unlock(&info->lock);
+ ret = do_mq_getsetattr(mqdes, new, old);
+ if (ret || !old)
+ return ret;
- ret = 0;
- if (u_omqstat != NULL && copy_to_user(u_omqstat, &omqstat,
- sizeof(struct mq_attr)))
- ret = -EFAULT;
+ if (put_compat_mq_attr(old, u_omqstat))
+ return -EFAULT;
+ return 0;
+}
+#endif
-out_fput:
- fdput(f);
-out:
- return ret;
+#ifdef CONFIG_COMPAT_32BIT_TIME
+static int compat_prepare_timeout(const struct old_timespec32 __user *p,
+ struct timespec64 *ts)
+{
+ if (get_old_timespec32(ts, p))
+ return -EFAULT;
+ if (!timespec64_valid(ts))
+ return -EINVAL;
+ return 0;
}
+SYSCALL_DEFINE5(mq_timedsend_time32, mqd_t, mqdes,
+ const char __user *, u_msg_ptr,
+ unsigned int, msg_len, unsigned int, msg_prio,
+ const struct old_timespec32 __user *, u_abs_timeout)
+{
+ struct timespec64 ts, *p = NULL;
+ if (u_abs_timeout) {
+ int res = compat_prepare_timeout(u_abs_timeout, &ts);
+ if (res)
+ return res;
+ p = &ts;
+ }
+ return do_mq_timedsend(mqdes, u_msg_ptr, msg_len, msg_prio, p);
+}
+
+SYSCALL_DEFINE5(mq_timedreceive_time32, mqd_t, mqdes,
+ char __user *, u_msg_ptr,
+ unsigned int, msg_len, unsigned int __user *, u_msg_prio,
+ const struct old_timespec32 __user *, u_abs_timeout)
+{
+ struct timespec64 ts, *p = NULL;
+ if (u_abs_timeout) {
+ int res = compat_prepare_timeout(u_abs_timeout, &ts);
+ if (res)
+ return res;
+ p = &ts;
+ }
+ return do_mq_timedreceive(mqdes, u_msg_ptr, msg_len, u_msg_prio, p);
+}
+#endif
+
static const struct inode_operations mqueue_dir_inode_operations = {
.lookup = simple_lookup,
.create = mqueue_create,
@@ -1385,20 +1606,27 @@ static const struct file_operations mqueue_file_operations = {
static const struct super_operations mqueue_super_ops = {
.alloc_inode = mqueue_alloc_inode,
- .destroy_inode = mqueue_destroy_inode,
+ .free_inode = mqueue_free_inode,
.evict_inode = mqueue_evict_inode,
.statfs = simple_statfs,
};
+static const struct fs_context_operations mqueue_fs_context_ops = {
+ .free = mqueue_fs_context_free,
+ .get_tree = mqueue_get_tree,
+};
+
static struct file_system_type mqueue_fs_type = {
- .name = "mqueue",
- .mount = mqueue_mount,
- .kill_sb = kill_litter_super,
- .fs_flags = FS_USERNS_MOUNT,
+ .name = "mqueue",
+ .init_fs_context = mqueue_init_fs_context,
+ .kill_sb = kill_anon_super,
+ .fs_flags = FS_USERNS_MOUNT,
};
int mq_init_ns(struct ipc_namespace *ns)
{
+ struct vfsmount *m;
+
ns->mq_queues_count = 0;
ns->mq_queues_max = DFLT_QUEUESMAX;
ns->mq_msg_max = DFLT_MSGMAX;
@@ -1406,12 +1634,10 @@ int mq_init_ns(struct ipc_namespace *ns)
ns->mq_msg_default = DFLT_MSG;
ns->mq_msgsize_default = DFLT_MSGSIZE;
- ns->mq_mnt = kern_mount_data(&mqueue_fs_type, ns);
- if (IS_ERR(ns->mq_mnt)) {
- int err = PTR_ERR(ns->mq_mnt);
- ns->mq_mnt = NULL;
- return err;
- }
+ m = mq_create_mount(ns);
+ if (IS_ERR(m))
+ return PTR_ERR(m);
+ ns->mq_mnt = m;
return 0;
}
@@ -1420,23 +1646,21 @@ void mq_clear_sbinfo(struct ipc_namespace *ns)
ns->mq_mnt->mnt_sb->s_fs_info = NULL;
}
-void mq_put_mnt(struct ipc_namespace *ns)
-{
- kern_unmount(ns->mq_mnt);
-}
-
static int __init init_mqueue_fs(void)
{
int error;
mqueue_inode_cachep = kmem_cache_create("mqueue_inode_cache",
sizeof(struct mqueue_inode_info), 0,
- SLAB_HWCACHE_ALIGN, init_once);
+ SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, init_once);
if (mqueue_inode_cachep == NULL)
return -ENOMEM;
- /* ignore failures - they are not fatal */
- mq_sysctl_table = mq_register_sysctl_table();
+ if (!setup_mq_sysctls(&init_ipc_ns)) {
+ pr_warn("sysctl registration failed\n");
+ error = -ENOMEM;
+ goto out_kmem;
+ }
error = register_filesystem(&mqueue_fs_type);
if (error)
@@ -1453,10 +1677,10 @@ static int __init init_mqueue_fs(void)
out_filesystem:
unregister_filesystem(&mqueue_fs_type);
out_sysctl:
- if (mq_sysctl_table)
- unregister_sysctl_table(mq_sysctl_table);
+ retire_mq_sysctls(&init_ipc_ns);
+out_kmem:
kmem_cache_destroy(mqueue_inode_cachep);
return error;
}
-__initcall(init_mqueue_fs);
+device_initcall(init_mqueue_fs);
generated by cgit (git 2.34.1) at 2025-12-22 02:03:23 +0000