/* * POSIX message queues filesystem for Linux. * * Copyright (C) 2003,2004 Krzysztof Benedyczak (golbi@mat.uni.torun.pl) * Michal Wronski (michal.wronski@gmail.com) * * Spinlocks: Mohamed Abbas (abbas.mohamed@intel.com) * Lockless receive & send, fd based notify: * Manfred Spraul (manfred@colorfullife.com) * * Audit: George Wilson (ltcgcw@us.ibm.com) * * This file is released under the GPL. */ #include <linux/capability.h>#include <linux/init.h>#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>#include <linux/mqueue.h>#include <linux/msg.h>#include <linux/skbuff.h>#include <linux/vmalloc.h>#include <linux/netlink.h>#include <linux/syscalls.h>#include <linux/audit.h>#include <linux/signal.h>#include <linux/mutex.h>#include <linux/nsproxy.h>#include <linux/pid.h>#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 #define SEND 0#define RECV 1 #define STATE_NONE 0#define STATE_READY 1 struct posix_msg_tree_node { struct rb_node rb_node; struct list_head msg_list; 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; struct msg_msg *msg; /* ptr of loaded message */ int state; /* one of STATE_* values */}; struct mqueue_inode_info { spinlock_t lock; struct inode vfs_inode; 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; u32 notify_self_exec_id; struct user_namespace *notify_user_ns; struct ucounts *ucounts; /* user who created, for accounting */ struct sock *notify_sock; struct sk_buff *notify_cookie; /* for tasks waiting for free space and messages, respectively */ struct ext_wait_queue e_wait_q[2]; 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 inline struct mqueue_inode_info *MQUEUE_I(struct inode *inode){ return container_of(inode, struct mqueue_inode_info, vfs_inode);} /* * This routine should be called with the mq_lock held. */static inline struct ipc_namespace *__get_ns_from_inode(struct inode *inode){ return get_ipc_ns(inode->i_sb->s_fs_info);} static struct ipc_namespace *get_ns_from_inode(struct inode *inode){ struct ipc_namespace *ns; spin_lock(&mq_lock); ns = __get_ns_from_inode(inode); spin_unlock(&mq_lock); return ns;} /* Auxiliary functions to manipulate messages' list */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) { parent = *p; leaf = rb_entry(parent, struct posix_msg_tree_node, rb_node); if (likely(leaf->priority == msg->m_type)) goto insert_msg; else if (msg->m_type < leaf->priority) { p = &(*p)->rb_left; rightmost = false; } else p = &(*p)->rb_right; } if (info->node_cache) { leaf = info->node_cache; info->node_cache = NULL; } else { leaf = kmalloc(sizeof(*leaf), GFP_ATOMIC); if (!leaf) return -ENOMEM; INIT_LIST_HEAD(&leaf->msg_list); } 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: info->attr.mq_curmsgs++; info->qsize += msg->m_ts; list_add_tail(&msg->m_list, &leaf->msg_list); 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 *parent = NULL; struct posix_msg_tree_node *leaf; struct msg_msg *msg; try_again: /* * 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, " "no tree element, but supposedly messages " "should exist!\n"); info->attr.mq_curmsgs = 0; } return NULL; } leaf = rb_entry(parent, struct posix_msg_tree_node, rb_node); if (unlikely(list_empty(&leaf->msg_list))) { pr_warn_once("Inconsistency in POSIX message queue, " "empty leaf node but we haven't implemented " "lazy leaf delete!\n"); 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)) { msg_tree_erase(leaf, info); } } info->attr.mq_curmsgs--; info->qsize -= msg->m_ts; return msg;} static struct inode *mqueue_get_inode(struct super_block *sb, struct ipc_namespace *ipc_ns, umode_t mode, struct mq_attr *attr){ struct inode *inode; int ret = -ENOMEM; inode = new_inode(sb); if (!inode) goto err; inode->i_ino = get_next_ino(); 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(inode); if (S_ISREG(mode)) { struct mqueue_inode_info *info; unsigned long mq_bytes, mq_treesize; inode->i_fop = &mqueue_file_operations; inode->i_size = FILENT_SIZE; /* mqueue specific info */ info = MQUEUE_I(inode); spin_lock_init(&info->lock); init_waitqueue_head(&info->wait_q); INIT_LIST_HEAD(&info->e_wait_q[0].list); INIT_LIST_HEAD(&info->e_wait_q[1].list); info->notify_owner = NULL; info->notify_user_ns = NULL; info->qsize = 0; 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, ipc_ns->mq_msg_default); info->attr.mq_msgsize = min(ipc_ns->mq_msgsize_max, ipc_ns->mq_msgsize_default); if (attr) { info->attr.mq_maxmsg = attr->mq_maxmsg; info->attr.mq_msgsize = attr->mq_msgsize; } /* * We used to allocate a static array of pointers and account * the size of that array as well as one msg_msg struct per * possible message into the queue size. That's no longer * accurate as the queue is now an rbtree and will grow and * shrink depending on usage patterns. We can, however, still * account one msg_msg struct per message, but the nodes are * allocated depending on priority usage, and most programs * only use one, or a handful, of priorities. However, since * this is pinned memory, we need to assume worst case, so * 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 = 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); } } else if (S_ISDIR(mode)) { inc_nlink(inode); /* Some things misbehave if size == 0 on a directory */ inode->i_size = 2 * DIRENT_SIZE; inode->i_op = &mqueue_dir_inode_operations; inode->i_fop = &simple_dir_operations; } return inode;out_inode: iput(inode);err: return ERR_PTR(ret);} static int mqueue_fill_super(struct super_block *sb, struct fs_context *fc){ struct inode *inode; struct ipc_namespace *ns = sb->s_fs_info; 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; inode = mqueue_get_inode(sb, ns, S_IFDIR | S_ISVTX | S_IRWXUGO, NULL); if (IS_ERR(inode)) return PTR_ERR(inode); sb->s_root = d_make_root(inode); if (!sb->s_root) return -ENOMEM; return 0;} static int mqueue_get_tree(struct fs_context *fc){ struct mqueue_fs_context *ctx = fc->fs_private; /* * 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 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(fc); put_fs_context(fc); return mnt;} static void init_once(void *foo){ struct mqueue_inode_info *p = foo; inode_init_once(&p->vfs_inode);} static struct inode *mqueue_alloc_inode(struct super_block *sb){ struct mqueue_inode_info *ei; Lines 1–500 of 1749. Load more
/* * POSIX message queues filesystem for Linux. * * Copyright (C) 2003,2004 Krzysztof Benedyczak (golbi@mat.uni.torun.pl) * Michal Wronski (michal.wronski@gmail.com) * * Spinlocks: Mohamed Abbas (abbas.mohamed@intel.com) * Lockless receive & send, fd based notify: * Manfred Spraul (manfred@colorfullife.com) * * Audit: George Wilson (ltcgcw@us.ibm.com) * * This file is released under the GPL. */ #include <linux/capability.h> #include <linux/init.h> #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> #include <linux/mqueue.h> #include <linux/msg.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/netlink.h> #include <linux/syscalls.h> #include <linux/audit.h> #include <linux/signal.h> #include <linux/mutex.h> #include <linux/nsproxy.h> #include <linux/pid.h> #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 #define SEND 0 #define RECV 1 #define STATE_NONE 0 #define STATE_READY 1 struct posix_msg_tree_node { struct rb_node rb_node; struct list_head msg_list; 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; struct msg_msg *msg; /* ptr of loaded message */ int state; /* one of STATE_* values */ }; struct mqueue_inode_info { spinlock_t lock; struct inode vfs_inode; 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; u32 notify_self_exec_id; struct user_namespace *notify_user_ns; struct ucounts *ucounts; /* user who created, for accounting */ struct sock *notify_sock; struct sk_buff *notify_cookie; /* for tasks waiting for free space and messages, respectively */ struct ext_wait_queue e_wait_q[2]; 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 inline struct mqueue_inode_info *MQUEUE_I(struct inode *inode) { return container_of(inode, struct mqueue_inode_info, vfs_inode); } /* * This routine should be called with the mq_lock held. */ static inline struct ipc_namespace *__get_ns_from_inode(struct inode *inode) { return get_ipc_ns(inode->i_sb->s_fs_info); } static struct ipc_namespace *get_ns_from_inode(struct inode *inode) { struct ipc_namespace *ns; spin_lock(&mq_lock); ns = __get_ns_from_inode(inode); spin_unlock(&mq_lock); return ns; } /* Auxiliary functions to manipulate messages' list */ 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) { parent = *p; leaf = rb_entry(parent, struct posix_msg_tree_node, rb_node); if (likely(leaf->priority == msg->m_type)) goto insert_msg; else if (msg->m_type < leaf->priority) { p = &(*p)->rb_left; rightmost = false; } else p = &(*p)->rb_right; } if (info->node_cache) { leaf = info->node_cache; info->node_cache = NULL; } else { leaf = kmalloc(sizeof(*leaf), GFP_ATOMIC); if (!leaf) return -ENOMEM; INIT_LIST_HEAD(&leaf->msg_list); } 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: info->attr.mq_curmsgs++; info->qsize += msg->m_ts; list_add_tail(&msg->m_list, &leaf->msg_list); 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 *parent = NULL; struct posix_msg_tree_node *leaf; struct msg_msg *msg; try_again: /* * 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, " "no tree element, but supposedly messages " "should exist!\n"); info->attr.mq_curmsgs = 0; } return NULL; } leaf = rb_entry(parent, struct posix_msg_tree_node, rb_node); if (unlikely(list_empty(&leaf->msg_list))) { pr_warn_once("Inconsistency in POSIX message queue, " "empty leaf node but we haven't implemented " "lazy leaf delete!\n"); 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)) { msg_tree_erase(leaf, info); } } info->attr.mq_curmsgs--; info->qsize -= msg->m_ts; return msg; } static struct inode *mqueue_get_inode(struct super_block *sb, struct ipc_namespace *ipc_ns, umode_t mode, struct mq_attr *attr) { struct inode *inode; int ret = -ENOMEM; inode = new_inode(sb); if (!inode) goto err; inode->i_ino = get_next_ino(); 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(inode); if (S_ISREG(mode)) { struct mqueue_inode_info *info; unsigned long mq_bytes, mq_treesize; inode->i_fop = &mqueue_file_operations; inode->i_size = FILENT_SIZE; /* mqueue specific info */ info = MQUEUE_I(inode); spin_lock_init(&info->lock); init_waitqueue_head(&info->wait_q); INIT_LIST_HEAD(&info->e_wait_q[0].list); INIT_LIST_HEAD(&info->e_wait_q[1].list); info->notify_owner = NULL; info->notify_user_ns = NULL; info->qsize = 0; 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, ipc_ns->mq_msg_default); info->attr.mq_msgsize = min(ipc_ns->mq_msgsize_max, ipc_ns->mq_msgsize_default); if (attr) { info->attr.mq_maxmsg = attr->mq_maxmsg; info->attr.mq_msgsize = attr->mq_msgsize; } /* * We used to allocate a static array of pointers and account * the size of that array as well as one msg_msg struct per * possible message into the queue size. That's no longer * accurate as the queue is now an rbtree and will grow and * shrink depending on usage patterns. We can, however, still * account one msg_msg struct per message, but the nodes are * allocated depending on priority usage, and most programs * only use one, or a handful, of priorities. However, since * this is pinned memory, we need to assume worst case, so * 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 = 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); } } else if (S_ISDIR(mode)) { inc_nlink(inode); /* Some things misbehave if size == 0 on a directory */ inode->i_size = 2 * DIRENT_SIZE; inode->i_op = &mqueue_dir_inode_operations; inode->i_fop = &simple_dir_operations; } return inode; out_inode: iput(inode); err: return ERR_PTR(ret); } static int mqueue_fill_super(struct super_block *sb, struct fs_context *fc) { struct inode *inode; struct ipc_namespace *ns = sb->s_fs_info; 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; inode = mqueue_get_inode(sb, ns, S_IFDIR | S_ISVTX | S_IRWXUGO, NULL); if (IS_ERR(inode)) return PTR_ERR(inode); sb->s_root = d_make_root(inode); if (!sb->s_root) return -ENOMEM; return 0; } static int mqueue_get_tree(struct fs_context *fc) { struct mqueue_fs_context *ctx = fc->fs_private; /* * 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 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(fc); put_fs_context(fc); return mnt; } static void init_once(void *foo) { struct mqueue_inode_info *p = foo; inode_init_once(&p->vfs_inode); } static struct inode *mqueue_alloc_inode(struct super_block *sb) { struct mqueue_inode_info *ei;