diff options
Diffstat (limited to 'ipc')
| -rw-r--r-- | ipc/Makefile | 12 | ||||
| -rw-r--r-- | ipc/compat.c | 82 | ||||
| -rw-r--r-- | ipc/ipc_sysctl.c | 304 | ||||
| -rw-r--r-- | ipc/mq_sysctl.c | 133 | ||||
| -rw-r--r-- | ipc/mqueue.c | 1748 | ||||
| -rw-r--r-- | ipc/msg.c | 1376 | ||||
| -rw-r--r-- | ipc/msgutil.c | 184 | ||||
| -rw-r--r-- | ipc/namespace.c | 258 | ||||
| -rw-r--r-- | ipc/sem.c | 2484 | ||||
| -rw-r--r-- | ipc/shm.c | 1883 | ||||
| -rw-r--r-- | ipc/syscall.c | 211 | ||||
| -rw-r--r-- | ipc/util.c | 931 | ||||
| -rw-r--r-- | ipc/util.h | 291 |
13 files changed, 9897 insertions, 0 deletions
diff --git a/ipc/Makefile b/ipc/Makefile new file mode 100644 index 0000000000..c2558c430f --- /dev/null +++ b/ipc/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the linux ipc. +# + +obj-$(CONFIG_SYSVIPC_COMPAT) += compat.o +obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o syscall.o +obj-$(CONFIG_SYSVIPC_SYSCTL) += ipc_sysctl.o +obj-$(CONFIG_POSIX_MQUEUE) += mqueue.o msgutil.o +obj-$(CONFIG_IPC_NS) += namespace.o +obj-$(CONFIG_POSIX_MQUEUE_SYSCTL) += mq_sysctl.o + diff --git a/ipc/compat.c b/ipc/compat.c new file mode 100644 index 0000000000..5ab8225923 --- /dev/null +++ b/ipc/compat.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * 32 bit compatibility code for System V IPC + * + * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz) + * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) + * Copyright (C) 1999 Arun Sharma <arun.sharma@intel.com> + * Copyright (C) 2000 VA Linux Co + * Copyright (C) 2000 Don Dugger <n0ano@valinux.com> + * Copyright (C) 2000 Hewlett-Packard Co. + * Copyright (C) 2000 David Mosberger-Tang <davidm@hpl.hp.com> + * Copyright (C) 2000 Gerhard Tonn (ton@de.ibm.com) + * Copyright (C) 2000-2002 Andi Kleen, SuSE Labs (x86-64 port) + * Copyright (C) 2000 Silicon Graphics, Inc. + * Copyright (C) 2001 IBM + * Copyright (C) 2004 IBM Deutschland Entwicklung GmbH, IBM Corporation + * Copyright (C) 2004 Arnd Bergmann (arnd@arndb.de) + * + * This code is collected from the versions for sparc64, mips64, s390x, ia64, + * ppc64 and x86_64, all of which are based on the original sparc64 version + * by Jakub Jelinek. + * + */ +#include <linux/compat.h> +#include <linux/errno.h> +#include <linux/highuid.h> +#include <linux/init.h> +#include <linux/msg.h> +#include <linux/shm.h> +#include <linux/syscalls.h> +#include <linux/ptrace.h> + +#include <linux/mutex.h> +#include <linux/uaccess.h> + +#include "util.h" + +int get_compat_ipc64_perm(struct ipc64_perm *to, + struct compat_ipc64_perm __user *from) +{ + struct compat_ipc64_perm v; + if (copy_from_user(&v, from, sizeof(v))) + return -EFAULT; + to->uid = v.uid; + to->gid = v.gid; + to->mode = v.mode; + return 0; +} + +int get_compat_ipc_perm(struct ipc64_perm *to, + struct compat_ipc_perm __user *from) +{ + struct compat_ipc_perm v; + if (copy_from_user(&v, from, sizeof(v))) + return -EFAULT; + to->uid = v.uid; + to->gid = v.gid; + to->mode = v.mode; + return 0; +} + +void to_compat_ipc64_perm(struct compat_ipc64_perm *to, struct ipc64_perm *from) +{ + to->key = from->key; + to->uid = from->uid; + to->gid = from->gid; + to->cuid = from->cuid; + to->cgid = from->cgid; + to->mode = from->mode; + to->seq = from->seq; +} + +void to_compat_ipc_perm(struct compat_ipc_perm *to, struct ipc64_perm *from) +{ + to->key = from->key; + SET_UID(to->uid, from->uid); + SET_GID(to->gid, from->gid); + SET_UID(to->cuid, from->cuid); + SET_GID(to->cgid, from->cgid); + to->mode = from->mode; + to->seq = from->seq; +} diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c new file mode 100644 index 0000000000..8c62e443f7 --- /dev/null +++ b/ipc/ipc_sysctl.c @@ -0,0 +1,304 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2007 + * + * Author: Eric Biederman <ebiederm@xmision.com> + */ + +#include <linux/module.h> +#include <linux/ipc.h> +#include <linux/nsproxy.h> +#include <linux/sysctl.h> +#include <linux/uaccess.h> +#include <linux/capability.h> +#include <linux/ipc_namespace.h> +#include <linux/msg.h> +#include <linux/slab.h> +#include "util.h" + +static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct ipc_namespace *ns = + container_of(table->data, struct ipc_namespace, shm_rmid_forced); + int err; + + err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + if (err < 0) + return err; + if (ns->shm_rmid_forced) + shm_destroy_orphaned(ns); + return err; +} + +static int proc_ipc_auto_msgmni(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table ipc_table; + int dummy = 0; + + memcpy(&ipc_table, table, sizeof(ipc_table)); + ipc_table.data = &dummy; + + if (write) + pr_info_once("writing to auto_msgmni has no effect"); + + return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos); +} + +static int proc_ipc_sem_dointvec(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct ipc_namespace *ns = + container_of(table->data, struct ipc_namespace, sem_ctls); + int ret, semmni; + + semmni = ns->sem_ctls[3]; + ret = proc_dointvec(table, write, buffer, lenp, ppos); + + if (!ret) + ret = sem_check_semmni(ns); + + /* + * Reset the semmni value if an error happens. + */ + if (ret) + ns->sem_ctls[3] = semmni; + return ret; +} + +int ipc_mni = IPCMNI; +int ipc_mni_shift = IPCMNI_SHIFT; +int ipc_min_cycle = RADIX_TREE_MAP_SIZE; + +static struct ctl_table ipc_sysctls[] = { + { + .procname = "shmmax", + .data = &init_ipc_ns.shm_ctlmax, + .maxlen = sizeof(init_ipc_ns.shm_ctlmax), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { + .procname = "shmall", + .data = &init_ipc_ns.shm_ctlall, + .maxlen = sizeof(init_ipc_ns.shm_ctlall), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { + .procname = "shmmni", + .data = &init_ipc_ns.shm_ctlmni, + .maxlen = sizeof(init_ipc_ns.shm_ctlmni), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &ipc_mni, + }, + { + .procname = "shm_rmid_forced", + .data = &init_ipc_ns.shm_rmid_forced, + .maxlen = sizeof(init_ipc_ns.shm_rmid_forced), + .mode = 0644, + .proc_handler = proc_ipc_dointvec_minmax_orphans, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "msgmax", + .data = &init_ipc_ns.msg_ctlmax, + .maxlen = sizeof(init_ipc_ns.msg_ctlmax), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_INT_MAX, + }, + { + .procname = "msgmni", + .data = &init_ipc_ns.msg_ctlmni, + .maxlen = sizeof(init_ipc_ns.msg_ctlmni), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &ipc_mni, + }, + { + .procname = "auto_msgmni", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_ipc_auto_msgmni, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "msgmnb", + .data = &init_ipc_ns.msg_ctlmnb, + .maxlen = sizeof(init_ipc_ns.msg_ctlmnb), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_INT_MAX, + }, + { + .procname = "sem", + .data = &init_ipc_ns.sem_ctls, + .maxlen = 4*sizeof(int), + .mode = 0644, + .proc_handler = proc_ipc_sem_dointvec, + }, +#ifdef CONFIG_CHECKPOINT_RESTORE + { + .procname = "sem_next_id", + .data = &init_ipc_ns.ids[IPC_SEM_IDS].next_id, + .maxlen = sizeof(init_ipc_ns.ids[IPC_SEM_IDS].next_id), + .mode = 0444, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_INT_MAX, + }, + { + .procname = "msg_next_id", + .data = &init_ipc_ns.ids[IPC_MSG_IDS].next_id, + .maxlen = sizeof(init_ipc_ns.ids[IPC_MSG_IDS].next_id), + .mode = 0444, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_INT_MAX, + }, + { + .procname = "shm_next_id", + .data = &init_ipc_ns.ids[IPC_SHM_IDS].next_id, + .maxlen = sizeof(init_ipc_ns.ids[IPC_SHM_IDS].next_id), + .mode = 0444, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_INT_MAX, + }, +#endif + {} +}; + +static struct ctl_table_set *set_lookup(struct ctl_table_root *root) +{ + return ¤t->nsproxy->ipc_ns->ipc_set; +} + +static int set_is_seen(struct ctl_table_set *set) +{ + return ¤t->nsproxy->ipc_ns->ipc_set == set; +} + +static int ipc_permissions(struct ctl_table_header *head, struct ctl_table *table) +{ + int mode = table->mode; + +#ifdef CONFIG_CHECKPOINT_RESTORE + struct ipc_namespace *ns = current->nsproxy->ipc_ns; + + if (((table->data == &ns->ids[IPC_SEM_IDS].next_id) || + (table->data == &ns->ids[IPC_MSG_IDS].next_id) || + (table->data == &ns->ids[IPC_SHM_IDS].next_id)) && + checkpoint_restore_ns_capable(ns->user_ns)) + mode = 0666; +#endif + return mode; +} + +static struct ctl_table_root set_root = { + .lookup = set_lookup, + .permissions = ipc_permissions, +}; + +bool setup_ipc_sysctls(struct ipc_namespace *ns) +{ + struct ctl_table *tbl; + + setup_sysctl_set(&ns->ipc_set, &set_root, set_is_seen); + + tbl = kmemdup(ipc_sysctls, sizeof(ipc_sysctls), GFP_KERNEL); + if (tbl) { + int i; + + for (i = 0; i < ARRAY_SIZE(ipc_sysctls); i++) { + if (tbl[i].data == &init_ipc_ns.shm_ctlmax) + tbl[i].data = &ns->shm_ctlmax; + + else if (tbl[i].data == &init_ipc_ns.shm_ctlall) + tbl[i].data = &ns->shm_ctlall; + + else if (tbl[i].data == &init_ipc_ns.shm_ctlmni) + tbl[i].data = &ns->shm_ctlmni; + + else if (tbl[i].data == &init_ipc_ns.shm_rmid_forced) + tbl[i].data = &ns->shm_rmid_forced; + + else if (tbl[i].data == &init_ipc_ns.msg_ctlmax) + tbl[i].data = &ns->msg_ctlmax; + + else if (tbl[i].data == &init_ipc_ns.msg_ctlmni) + tbl[i].data = &ns->msg_ctlmni; + + else if (tbl[i].data == &init_ipc_ns.msg_ctlmnb) + tbl[i].data = &ns->msg_ctlmnb; + + else if (tbl[i].data == &init_ipc_ns.sem_ctls) + tbl[i].data = &ns->sem_ctls; +#ifdef CONFIG_CHECKPOINT_RESTORE + else if (tbl[i].data == &init_ipc_ns.ids[IPC_SEM_IDS].next_id) + tbl[i].data = &ns->ids[IPC_SEM_IDS].next_id; + + else if (tbl[i].data == &init_ipc_ns.ids[IPC_MSG_IDS].next_id) + tbl[i].data = &ns->ids[IPC_MSG_IDS].next_id; + + else if (tbl[i].data == &init_ipc_ns.ids[IPC_SHM_IDS].next_id) + tbl[i].data = &ns->ids[IPC_SHM_IDS].next_id; +#endif + else + tbl[i].data = NULL; + } + + ns->ipc_sysctls = __register_sysctl_table(&ns->ipc_set, + "kernel", tbl, + ARRAY_SIZE(ipc_sysctls)); + } + if (!ns->ipc_sysctls) { + kfree(tbl); + retire_sysctl_set(&ns->ipc_set); + return false; + } + + return true; +} + +void retire_ipc_sysctls(struct ipc_namespace *ns) +{ + struct ctl_table *tbl; + + tbl = ns->ipc_sysctls->ctl_table_arg; + unregister_sysctl_table(ns->ipc_sysctls); + retire_sysctl_set(&ns->ipc_set); + kfree(tbl); +} + +static int __init ipc_sysctl_init(void) +{ + if (!setup_ipc_sysctls(&init_ipc_ns)) { + pr_warn("ipc sysctl registration failed\n"); + return -ENOMEM; + } + return 0; +} + +device_initcall(ipc_sysctl_init); + +static int __init ipc_mni_extend(char *str) +{ + ipc_mni = IPCMNI_EXTEND; + ipc_mni_shift = IPCMNI_EXTEND_SHIFT; + ipc_min_cycle = IPCMNI_EXTEND_MIN_CYCLE; + pr_info("IPCMNI extended to %d.\n", ipc_mni); + return 0; +} +early_param("ipcmni_extend", ipc_mni_extend); diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c new file mode 100644 index 0000000000..ebb5ed81c1 --- /dev/null +++ b/ipc/mq_sysctl.c @@ -0,0 +1,133 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2007 IBM Corporation + * + * Author: Cedric Le Goater <clg@fr.ibm.com> + */ + +#include <linux/nsproxy.h> +#include <linux/ipc_namespace.h> +#include <linux/sysctl.h> + +#include <linux/stat.h> +#include <linux/capability.h> +#include <linux/slab.h> + +static int msg_max_limit_min = MIN_MSGMAX; +static int msg_max_limit_max = HARD_MSGMAX; + +static int msg_maxsize_limit_min = MIN_MSGSIZEMAX; +static int msg_maxsize_limit_max = HARD_MSGSIZEMAX; + +static struct ctl_table mq_sysctls[] = { + { + .procname = "queues_max", + .data = &init_ipc_ns.mq_queues_max, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "msg_max", + .data = &init_ipc_ns.mq_msg_max, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &msg_max_limit_min, + .extra2 = &msg_max_limit_max, + }, + { + .procname = "msgsize_max", + .data = &init_ipc_ns.mq_msgsize_max, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &msg_maxsize_limit_min, + .extra2 = &msg_maxsize_limit_max, + }, + { + .procname = "msg_default", + .data = &init_ipc_ns.mq_msg_default, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &msg_max_limit_min, + .extra2 = &msg_max_limit_max, + }, + { + .procname = "msgsize_default", + .data = &init_ipc_ns.mq_msgsize_default, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &msg_maxsize_limit_min, + .extra2 = &msg_maxsize_limit_max, + }, + {} +}; + +static struct ctl_table_set *set_lookup(struct ctl_table_root *root) +{ + return ¤t->nsproxy->ipc_ns->mq_set; +} + +static int set_is_seen(struct ctl_table_set *set) +{ + return ¤t->nsproxy->ipc_ns->mq_set == set; +} + +static struct ctl_table_root set_root = { + .lookup = set_lookup, +}; + +bool setup_mq_sysctls(struct ipc_namespace *ns) +{ + struct ctl_table *tbl; + + setup_sysctl_set(&ns->mq_set, &set_root, set_is_seen); + + tbl = kmemdup(mq_sysctls, sizeof(mq_sysctls), GFP_KERNEL); + if (tbl) { + int i; + + for (i = 0; i < ARRAY_SIZE(mq_sysctls); i++) { + if (tbl[i].data == &init_ipc_ns.mq_queues_max) + tbl[i].data = &ns->mq_queues_max; + + else if (tbl[i].data == &init_ipc_ns.mq_msg_max) + tbl[i].data = &ns->mq_msg_max; + + else if (tbl[i].data == &init_ipc_ns.mq_msgsize_max) + tbl[i].data = &ns->mq_msgsize_max; + + else if (tbl[i].data == &init_ipc_ns.mq_msg_default) + tbl[i].data = &ns->mq_msg_default; + + else if (tbl[i].data == &init_ipc_ns.mq_msgsize_default) + tbl[i].data = &ns->mq_msgsize_default; + else + tbl[i].data = NULL; + } + + ns->mq_sysctls = __register_sysctl_table(&ns->mq_set, + "fs/mqueue", tbl, + ARRAY_SIZE(mq_sysctls)); + } + if (!ns->mq_sysctls) { + kfree(tbl); + retire_sysctl_set(&ns->mq_set); + return false; + } + + return true; +} + +void retire_mq_sysctls(struct ipc_namespace *ns) +{ + struct ctl_table *tbl; + + tbl = ns->mq_sysctls->ctl_table_arg; + unregister_sysctl_table(ns->mq_sysctls); + retire_sysctl_set(&ns->mq_set); + kfree(tbl); +} diff --git a/ipc/mqueue.c b/ipc/mqueue.c new file mode 100644 index 0000000000..ba8215ed66 --- /dev/null +++ b/ipc/mqueue.c @@ -0,0 +1,1748 @@ +/* + * 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_atime = inode_set_ctime_current(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; + + ei = alloc_inode_sb(sb, mqueue_inode_cachep, GFP_KERNEL); + if (!ei) + return NULL; + return &ei->vfs_inode; +} + +static void mqueue_free_inode(struct inode *inode) +{ + kmem_cache_free(mqueue_inode_cachep, MQUEUE_I(inode)); +} + +static void mqueue_evict_inode(struct inode *inode) +{ + struct mqueue_inode_info *info; + struct ipc_namespace *ipc_ns; + struct msg_msg *msg, *nmsg; + LIST_HEAD(tmp_msg); + + clear_inode(inode); + + if (S_ISDIR(inode->i_mode)) + return; + + ipc_ns = get_ns_from_inode(inode); + info = MQUEUE_I(inode); + spin_lock(&info->lock); + while ((msg = msg_get(info)) != NULL) + list_add_tail(&msg->m_list, &tmp_msg); + kfree(info->node_cache); + spin_unlock(&info->lock); + + 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; + + /* 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); + + spin_lock(&mq_lock); + 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 + * to which we now hold a reference, or it is NULL. + * We can't put it here under mq_lock, though. + */ + if (ipc_ns) + ipc_ns->mq_queues_count--; + spin_unlock(&mq_lock); + put_ucounts(info->ucounts); + info->ucounts = NULL; + } + if (ipc_ns) + put_ipc_ns(ipc_ns); +} + +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 = arg; + int error; + struct ipc_namespace *ipc_ns; + + spin_lock(&mq_lock); + ipc_ns = __get_ns_from_inode(dir); + if (!ipc_ns) { + error = -EACCES; + goto out_unlock; + } + + if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max && + !capable(CAP_SYS_RESOURCE)) { + error = -ENOSPC; + goto out_unlock; + } + ipc_ns->mq_queues_count++; + spin_unlock(&mq_lock); + + inode = mqueue_get_inode(dir->i_sb, ipc_ns, mode, attr); + if (IS_ERR(inode)) { + error = PTR_ERR(inode); + spin_lock(&mq_lock); + ipc_ns->mq_queues_count--; + goto out_unlock; + } + + put_ipc_ns(ipc_ns); + dir->i_size += DIRENT_SIZE; + dir->i_mtime = dir->i_atime = inode_set_ctime_current(dir); + + d_instantiate(dentry, inode); + dget(dentry); + return 0; +out_unlock: + spin_unlock(&mq_lock); + if (ipc_ns) + put_ipc_ns(ipc_ns); + return error; +} + +static int mqueue_create(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) +{ + return mqueue_create_attr(dentry, mode, NULL); +} + +static int mqueue_unlink(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + + dir->i_mtime = dir->i_atime = inode_set_ctime_current(dir); + dir->i_size -= DIRENT_SIZE; + drop_nlink(inode); + dput(dentry); + return 0; +} + +/* +* This is routine for system read from queue file. +* To avoid mess with doing here some sort of mq_receive we allow +* to read only queue size & notification info (the only values +* that are interesting from user point of view and aren't accessible +* through std routines) +*/ +static ssize_t mqueue_read_file(struct file *filp, char __user *u_data, + size_t count, loff_t *off) +{ + struct inode *inode = file_inode(filp); + struct mqueue_inode_info *info = MQUEUE_I(inode); + char buffer[FILENT_SIZE]; + ssize_t ret; + + spin_lock(&info->lock); + snprintf(buffer, sizeof(buffer), + "QSIZE:%-10lu NOTIFY:%-5d SIGNO:%-5d NOTIFY_PID:%-6d\n", + info->qsize, + info->notify_owner ? info->notify.sigev_notify : 0, + (info->notify_owner && + info->notify.sigev_notify == SIGEV_SIGNAL) ? + info->notify.sigev_signo : 0, + pid_vnr(info->notify_owner)); + spin_unlock(&info->lock); + buffer[sizeof(buffer)-1] = '\0'; + + ret = simple_read_from_buffer(u_data, count, off, buffer, + strlen(buffer)); + if (ret <= 0) + return ret; + + inode->i_atime = inode_set_ctime_current(inode); + return ret; +} + +static int mqueue_flush_file(struct file *filp, fl_owner_t id) +{ + struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp)); + + spin_lock(&info->lock); + if (task_tgid(current) == info->notify_owner) + remove_notification(info); + + spin_unlock(&info->lock); + return 0; +} + +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)); + __poll_t retval = 0; + + poll_wait(filp, &info->wait_q, poll_tab); + + spin_lock(&info->lock); + if (info->attr.mq_curmsgs) + retval = EPOLLIN | EPOLLRDNORM; + + if (info->attr.mq_curmsgs < info->attr.mq_maxmsg) + retval |= EPOLLOUT | EPOLLWRNORM; + spin_unlock(&info->lock); + + return retval; +} + +/* Adds current to info->e_wait_q[sr] before element with smaller prio */ +static void wq_add(struct mqueue_inode_info *info, int sr, + struct ext_wait_queue *ewp) +{ + struct ext_wait_queue *walk; + + list_for_each_entry(walk, &info->e_wait_q[sr].list, list) { + if (walk->task->prio <= current->prio) { + list_add_tail(&ewp->list, &walk->list); + return; + } + } + list_add_tail(&ewp->list, &info->e_wait_q[sr].list); +} + +/* + * Puts current task to sleep. Caller must hold queue lock. After return + * lock isn't held. + * sr: SEND or RECV + */ +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; + + wq_add(info, sr, ewp); + + for (;;) { + /* 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); + + 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); + + /* we hold info->lock, so no memory barrier required */ + if (READ_ONCE(ewp->state) == STATE_READY) { + retval = 0; + goto out_unlock; + } + if (signal_pending(current)) { + retval = -ERESTARTSYS; + break; + } + if (time == 0) { + retval = -ETIMEDOUT; + break; + } + } + list_del(&ewp->list); +out_unlock: + spin_unlock(&info->lock); +out: + return retval; +} + +/* + * Returns waiting task that should be serviced first or NULL if none exists + */ +static struct ext_wait_queue *wq_get_first_waiter( + struct mqueue_inode_info *info, int sr) +{ + struct list_head *ptr; + + ptr = info->e_wait_q[sr].list.prev; + if (ptr == &info->e_wait_q[sr].list) + return NULL; + return list_entry(ptr, struct ext_wait_queue, list); +} + + +static inline void set_cookie(struct sk_buff *skb, char code) +{ + ((char *)skb->data)[NOTIFY_COOKIE_LEN-1] = code; +} + +/* + * The next function is only to split too long sys_mq_timedsend + */ +static void __do_notify(struct mqueue_inode_info *info) +{ + /* notification + * invoked when there is registered process and there isn't process + * waiting synchronously for message AND state of queue changed from + * empty to not empty. Here we are sure that no one is waiting + * synchronously. */ + if (info->notify_owner && + info->attr.mq_curmsgs == 1) { + switch (info->notify.sigev_notify) { + case SIGEV_NONE: + break; + 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; + 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()); + /* + * 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(); + break; + } + case SIGEV_THREAD: + set_cookie(info->notify_cookie, NOTIFY_WOKENUP); + netlink_sendskb(info->notify_sock, info->notify_cookie); + break; + } + /* after notification unregisters process */ + put_pid(info->notify_owner); + put_user_ns(info->notify_user_ns); + info->notify_owner = NULL; + info->notify_user_ns = NULL; + } + wake_up(&info->wait_q); +} + +static int prepare_timeout(const struct __kernel_timespec __user *u_abs_timeout, + struct timespec64 *ts) +{ + if (get_timespec64(ts, u_abs_timeout)) + return -EFAULT; + if (!timespec64_valid(ts)) + return -EINVAL; + return 0; +} + +static void remove_notification(struct mqueue_inode_info *info) +{ + if (info->notify_owner != NULL && + info->notify.sigev_notify == SIGEV_THREAD) { + set_cookie(info->notify_cookie, NOTIFY_REMOVED); + netlink_sendskb(info->notify_sock, info->notify_cookie); + } + put_pid(info->notify_owner); + put_user_ns(info->notify_user_ns); + info->notify_owner = NULL; + info->notify_user_ns = NULL; +} + +static int prepare_open(struct dentry *dentry, int oflag, int ro, + umode_t mode, struct filename *name, + struct mq_attr *attr) +{ + static const int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE, + MAY_READ | MAY_WRITE }; + int acc; + + 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); + } + /* 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); +} + +static int do_mq_open(const char __user *u_name, int oflag, umode_t mode, + struct mq_attr *attr) +{ + struct vfsmount *mnt = current->nsproxy->ipc_ns->mq_mnt; + struct dentry *root = mnt->mnt_root; + struct filename *name; + struct path path; + int fd, error; + int ro; + + audit_mq_open(oflag, mode, attr); + + 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 */ + inode_lock(d_inode(root)); + 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); + error = prepare_open(path.dentry, oflag, ro, mode, name, attr); + if (!error) { + struct file *file = dentry_open(&path, oflag, current_cred()); + if (!IS_ERR(file)) + fd_install(fd, file); + else + error = PTR_ERR(file); + } + path_put(&path); +out_putfd: + if (error) { + put_unused_fd(fd); + fd = error; + } + inode_unlock(d_inode(root)); + if (!ro) + mnt_drop_write(mnt); +out_putname: + putname(name); + return fd; +} + +SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, + struct mq_attr __user *, u_attr) +{ + struct mq_attr attr; + if (u_attr && copy_from_user(&attr, u_attr, sizeof(struct mq_attr))) + return -EFAULT; + + return do_mq_open(u_name, oflag, mode, u_attr ? &attr : NULL); +} + +SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) +{ + int err; + struct filename *name; + struct dentry *dentry; + struct inode *inode = NULL; + struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns; + struct vfsmount *mnt = ipc_ns->mq_mnt; + + name = getname(u_name); + if (IS_ERR(name)) + return PTR_ERR(name); + + audit_inode_parent_hidden(name, mnt->mnt_root); + err = mnt_want_write(mnt); + if (err) + goto out_name; + inode_lock_nested(d_inode(mnt->mnt_root), I_MUTEX_PARENT); + dentry = lookup_one_len(name->name, mnt->mnt_root, + strlen(name->name)); + if (IS_ERR(dentry)) { + err = PTR_ERR(dentry); + goto out_unlock; + } + + inode = d_inode(dentry); + if (!inode) { + err = -ENOENT; + } else { + ihold(inode); + err = vfs_unlink(&nop_mnt_idmap, d_inode(dentry->d_parent), + dentry, NULL); + } + dput(dentry); + +out_unlock: + inode_unlock(d_inode(mnt->mnt_root)); + iput(inode); + mnt_drop_write(mnt); +out_name: + putname(name); + + return err; +} + +/* Pipelined send and receive functions. + * + * If a receiver finds no waiting message, then it registers itself in the + * 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: + * + * - 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 wake_q_head *wake_q, + struct mqueue_inode_info *info, + struct msg_msg *message, + struct ext_wait_queue *receiver) +{ + receiver->msg = message; + __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 wake_q_head *wake_q, + struct mqueue_inode_info *info) +{ + struct ext_wait_queue *sender = wq_get_first_waiter(info, SEND); + + if (!sender) { + /* for poll */ + wake_up_interruptible(&info->wait_q); + return; + } + if (msg_insert(sender->msg, info)) + return; + + __pipelined_op(wake_q, info, sender); +} + +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 posix_msg_tree_node *new_leaf = NULL; + int ret = 0; + DEFINE_WAKE_Q(wake_q); + + if (unlikely(msg_prio >= (unsigned long) MQ_PRIO_MAX)) + return -EINVAL; + + if (ts) { + expires = timespec64_to_ktime(*ts); + timeout = &expires; + } + + audit_mq_sendrecv(mqdes, msg_len, msg_prio, ts); + + f = fdget(mqdes); + if (unlikely(!f.file)) { + ret = -EBADF; + goto out; + } + + inode = file_inode(f.file); + if (unlikely(f.file->f_op != &mqueue_file_operations)) { + ret = -EBADF; + goto out_fput; + } + info = MQUEUE_I(inode); + audit_file(f.file); + + if (unlikely(!(f.file->f_mode & FMODE_WRITE))) { + ret = -EBADF; + goto out_fput; + } + + if (unlikely(msg_len > info->attr.mq_msgsize)) { + ret = -EMSGSIZE; + goto out_fput; + } + + /* 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; + } + msg_ptr->m_ts = msg_len; + msg_ptr->m_type = msg_prio; + + /* + * msg_insert really wants us to have a valid, spare node struct so + * it doesn't have to kmalloc a GFP_ATOMIC allocation, but it will + * fall back to that if necessary. + */ + if (!info->node_cache) + new_leaf = kmalloc(sizeof(*new_leaf), GFP_KERNEL); + + spin_lock(&info->lock); + + if (!info->node_cache && new_leaf) { + /* Save our speculative allocation into the cache */ + INIT_LIST_HEAD(&new_leaf->msg_list); + info->node_cache = 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) { + ret = -EAGAIN; + } else { + wait.task = current; + wait.msg = (void *) msg_ptr; + + /* 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 + * returns with the lock released + */ + goto out_free; + } + } else { + receiver = wq_get_first_waiter(info, RECV); + if (receiver) { + pipelined_send(&wake_q, info, msg_ptr, receiver); + } else { + /* adds message to the queue */ + ret = msg_insert(msg_ptr, info); + if (ret) + goto out_unlock; + __do_notify(info); + } + inode->i_atime = inode->i_mtime = inode_set_ctime_current(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; +} + +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 posix_msg_tree_node *new_leaf = NULL; + + if (ts) { + expires = timespec64_to_ktime(*ts); + timeout = &expires; + } + + audit_mq_sendrecv(mqdes, msg_len, 0, ts); + + f = fdget(mqdes); + if (unlikely(!f.file)) { + ret = -EBADF; + goto out; + } + + inode = file_inode(f.file); + if (unlikely(f.file->f_op != &mqueue_file_operations)) { + ret = -EBADF; + goto out_fput; + } + info = MQUEUE_I(inode); + audit_file(f.file); + + if (unlikely(!(f.file->f_mode & FMODE_READ))) { + ret = -EBADF; + goto out_fput; + } + + /* checks if buffer is big enough */ + if (unlikely(msg_len < info->attr.mq_msgsize)) { + ret = -EMSGSIZE; + goto out_fput; + } + + /* + * msg_insert really wants us to have a valid, spare node struct so + * it doesn't have to kmalloc a GFP_ATOMIC allocation, but it will + * fall back to that if necessary. + */ + if (!info->node_cache) + new_leaf = kmalloc(sizeof(*new_leaf), GFP_KERNEL); + + spin_lock(&info->lock); + + if (!info->node_cache && new_leaf) { + /* Save our speculative allocation into the cache */ + INIT_LIST_HEAD(&new_leaf->msg_list); + info->node_cache = new_leaf; + } else { + kfree(new_leaf); + } + + if (info->attr.mq_curmsgs == 0) { + if (f.file->f_flags & O_NONBLOCK) { + spin_unlock(&info->lock); + ret = -EAGAIN; + } else { + wait.task = current; + + /* 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_set_ctime_current(inode); + + /* There is now free space in queue. */ + pipelined_receive(&wake_q, info); + spin_unlock(&info->lock); + wake_up_q(&wake_q); + ret = 0; + } + if (ret == 0) { + ret = msg_ptr->m_ts; + + if ((u_msg_prio && put_user(msg_ptr->m_type, u_msg_prio)) || + store_msg(u_msg_ptr, msg_ptr, msg_ptr->m_ts)) { + ret = -EFAULT; + } + 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. + */ +static int do_mq_notify(mqd_t mqdes, const struct sigevent *notification) +{ + int ret; + struct fd f; + struct sock *sock; + struct inode *inode; + struct mqueue_inode_info *info; + struct sk_buff *nc; + + audit_mq_notify(mqdes, notification); + + nc = NULL; + sock = NULL; + 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)) { + return -EINVAL; + } + if (notification->sigev_notify == SIGEV_THREAD) { + long timeo; + + /* create the notify skb */ + nc = alloc_skb(NOTIFY_COOKIE_LEN, GFP_KERNEL); + if (!nc) + return -ENOMEM; + + if (copy_from_user(nc->data, + notification->sigev_value.sival_ptr, + NOTIFY_COOKIE_LEN)) { + ret = -EFAULT; + goto free_skb; + } + + /* 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); + if (IS_ERR(sock)) { + ret = PTR_ERR(sock); + goto free_skb; + } + + timeo = MAX_SCHEDULE_TIMEOUT; + ret = netlink_attachskb(sock, nc, &timeo, NULL); + if (ret == 1) { + sock = NULL; + goto retry; + } + if (ret) + return ret; + } + } + + f = fdget(mqdes); + if (!f.file) { + ret = -EBADF; + goto out; + } + + inode = file_inode(f.file); + if (unlikely(f.file->f_op != &mqueue_file_operations)) { + ret = -EBADF; + goto out_fput; + } + info = MQUEUE_I(inode); + + ret = 0; + spin_lock(&info->lock); + if (notification == NULL) { + if (info->notify_owner == task_tgid(current)) { + remove_notification(info); + inode->i_atime = inode_set_ctime_current(inode); + } + } else if (info->notify_owner != NULL) { + ret = -EBUSY; + } else { + switch (notification->sigev_notify) { + case SIGEV_NONE: + info->notify.sigev_notify = SIGEV_NONE; + break; + case SIGEV_THREAD: + info->notify_sock = sock; + info->notify_cookie = nc; + sock = NULL; + nc = NULL; + 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_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_set_ctime_current(inode); + } + spin_unlock(&info->lock); +out_fput: + fdput(f); +out: + if (sock) + netlink_detachskb(sock, nc); + else +free_skb: + 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 fd f; + struct inode *inode; + struct mqueue_inode_info *info; + + if (new && (new->mq_flags & (~O_NONBLOCK))) + return -EINVAL; + + f = fdget(mqdes); + if (!f.file) + return -EBADF; + + if (unlikely(f.file->f_op != &mqueue_file_operations)) { + fdput(f); + return -EBADF; + } + + inode = file_inode(f.file); + info = MQUEUE_I(inode); + + spin_lock(&info->lock); + + if (old) { + *old = info->attr; + old->mq_flags = f.file->f_flags & O_NONBLOCK; + } + if (new) { + audit_mq_getsetattr(mqdes, new); + spin_lock(&f.file->f_lock); + if (new->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_set_ctime_current(inode); + } + + spin_unlock(&info->lock); + fdput(f); + 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 mq_attr *new = NULL, *old = NULL; + + if (u_mqstat) { + new = &mqstat; + if (copy_from_user(new, u_mqstat, sizeof(struct mq_attr))) + return -EFAULT; + } + if (u_omqstat) + old = &omqstat; + + 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); +} + +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; + } + return do_mq_notify(mqdes, p); +} + +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; + + if (u_mqstat) { + new = &mqstat; + if (get_compat_mq_attr(new, u_mqstat)) + return -EFAULT; + } + if (u_omqstat) + old = &omqstat; + + ret = do_mq_getsetattr(mqdes, new, old); + if (ret || !old) + return ret; + + if (put_compat_mq_attr(old, u_omqstat)) + return -EFAULT; + return 0; +} +#endif + +#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, + .unlink = mqueue_unlink, +}; + +static const struct file_operations mqueue_file_operations = { + .flush = mqueue_flush_file, + .poll = mqueue_poll_file, + .read = mqueue_read_file, + .llseek = default_llseek, +}; + +static const struct super_operations mqueue_super_ops = { + .alloc_inode = mqueue_alloc_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", + .init_fs_context = mqueue_init_fs_context, + .kill_sb = kill_litter_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; + ns->mq_msgsize_max = DFLT_MSGSIZEMAX; + ns->mq_msg_default = DFLT_MSG; + ns->mq_msgsize_default = DFLT_MSGSIZE; + + m = mq_create_mount(ns); + if (IS_ERR(m)) + return PTR_ERR(m); + ns->mq_mnt = m; + return 0; +} + +void mq_clear_sbinfo(struct ipc_namespace *ns) +{ + ns->mq_mnt->mnt_sb->s_fs_info = NULL; +} + +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|SLAB_ACCOUNT, init_once); + if (mqueue_inode_cachep == NULL) + return -ENOMEM; + + 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) + goto out_sysctl; + + spin_lock_init(&mq_lock); + + error = mq_init_ns(&init_ipc_ns); + if (error) + goto out_filesystem; + + return 0; + +out_filesystem: + unregister_filesystem(&mqueue_fs_type); +out_sysctl: + retire_mq_sysctls(&init_ipc_ns); +out_kmem: + kmem_cache_destroy(mqueue_inode_cachep); + return error; +} + +device_initcall(init_mqueue_fs); diff --git a/ipc/msg.c b/ipc/msg.c new file mode 100644 index 0000000000..fd08b3cb36 --- /dev/null +++ b/ipc/msg.c @@ -0,0 +1,1376 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/ipc/msg.c + * Copyright (C) 1992 Krishna Balasubramanian + * + * Removed all the remaining kerneld mess + * Catch the -EFAULT stuff properly + * Use GFP_KERNEL for messages as in 1.2 + * Fixed up the unchecked user space derefs + * Copyright (C) 1998 Alan Cox & Andi Kleen + * + * /proc/sysvipc/msg support (c) 1999 Dragos Acostachioaie <dragos@iname.com> + * + * mostly rewritten, threaded and wake-one semantics added + * MSGMAX limit removed, sysctl's added + * (c) 1999 Manfred Spraul <manfred@colorfullife.com> + * + * support for audit of ipc object properties and permission changes + * Dustin Kirkland <dustin.kirkland@us.ibm.com> + * + * namespaces support + * OpenVZ, SWsoft Inc. + * Pavel Emelianov <xemul@openvz.org> + */ + +#include <linux/capability.h> +#include <linux/msg.h> +#include <linux/spinlock.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/proc_fs.h> +#include <linux/list.h> +#include <linux/security.h> +#include <linux/sched/wake_q.h> +#include <linux/syscalls.h> +#include <linux/audit.h> +#include <linux/seq_file.h> +#include <linux/rwsem.h> +#include <linux/nsproxy.h> +#include <linux/ipc_namespace.h> +#include <linux/rhashtable.h> +#include <linux/percpu_counter.h> + +#include <asm/current.h> +#include <linux/uaccess.h> +#include "util.h" + +/* one msq_queue structure for each present queue on the system */ +struct msg_queue { + struct kern_ipc_perm q_perm; + time64_t q_stime; /* last msgsnd time */ + time64_t q_rtime; /* last msgrcv time */ + time64_t q_ctime; /* last change time */ + unsigned long q_cbytes; /* current number of bytes on queue */ + unsigned long q_qnum; /* number of messages in queue */ + unsigned long q_qbytes; /* max number of bytes on queue */ + struct pid *q_lspid; /* pid of last msgsnd */ + struct pid *q_lrpid; /* last receive pid */ + + struct list_head q_messages; + struct list_head q_receivers; + struct list_head q_senders; +} __randomize_layout; + +/* + * MSG_BARRIER Locking: + * + * Similar to the optimization used in ipc/mqueue.c, one syscall return path + * does not acquire any locks when it sees that a message exists in + * msg_receiver.r_msg. Therefore r_msg is set using smp_store_release() + * and accessed using READ_ONCE()+smp_acquire__after_ctrl_dep(). In addition, + * wake_q_add_safe() is used. See ipc/mqueue.c for more details + */ + +/* one msg_receiver structure for each sleeping receiver */ +struct msg_receiver { + struct list_head r_list; + struct task_struct *r_tsk; + + int r_mode; + long r_msgtype; + long r_maxsize; + + struct msg_msg *r_msg; +}; + +/* one msg_sender for each sleeping sender */ +struct msg_sender { + struct list_head list; + struct task_struct *tsk; + size_t msgsz; +}; + +#define SEARCH_ANY 1 +#define SEARCH_EQUAL 2 +#define SEARCH_NOTEQUAL 3 +#define SEARCH_LESSEQUAL 4 +#define SEARCH_NUMBER 5 + +#define msg_ids(ns) ((ns)->ids[IPC_MSG_IDS]) + +static inline struct msg_queue *msq_obtain_object(struct ipc_namespace *ns, int id) +{ + struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&msg_ids(ns), id); + + if (IS_ERR(ipcp)) + return ERR_CAST(ipcp); + + return container_of(ipcp, struct msg_queue, q_perm); +} + +static inline struct msg_queue *msq_obtain_object_check(struct ipc_namespace *ns, + int id) +{ + struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&msg_ids(ns), id); + + if (IS_ERR(ipcp)) + return ERR_CAST(ipcp); + + return container_of(ipcp, struct msg_queue, q_perm); +} + +static inline void msg_rmid(struct ipc_namespace *ns, struct msg_queue *s) +{ + ipc_rmid(&msg_ids(ns), &s->q_perm); +} + +static void msg_rcu_free(struct rcu_head *head) +{ + struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu); + struct msg_queue *msq = container_of(p, struct msg_queue, q_perm); + + security_msg_queue_free(&msq->q_perm); + kfree(msq); +} + +/** + * newque - Create a new msg queue + * @ns: namespace + * @params: ptr to the structure that contains the key and msgflg + * + * Called with msg_ids.rwsem held (writer) + */ +static int newque(struct ipc_namespace *ns, struct ipc_params *params) +{ + struct msg_queue *msq; + int retval; + key_t key = params->key; + int msgflg = params->flg; + + msq = kmalloc(sizeof(*msq), GFP_KERNEL_ACCOUNT); + if (unlikely(!msq)) + return -ENOMEM; + + msq->q_perm.mode = msgflg & S_IRWXUGO; + msq->q_perm.key = key; + + msq->q_perm.security = NULL; + retval = security_msg_queue_alloc(&msq->q_perm); + if (retval) { + kfree(msq); + return retval; + } + + msq->q_stime = msq->q_rtime = 0; + msq->q_ctime = ktime_get_real_seconds(); + msq->q_cbytes = msq->q_qnum = 0; + msq->q_qbytes = ns->msg_ctlmnb; + msq->q_lspid = msq->q_lrpid = NULL; + INIT_LIST_HEAD(&msq->q_messages); + INIT_LIST_HEAD(&msq->q_receivers); + INIT_LIST_HEAD(&msq->q_senders); + + /* ipc_addid() locks msq upon success. */ + retval = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni); + if (retval < 0) { + ipc_rcu_putref(&msq->q_perm, msg_rcu_free); + return retval; + } + + ipc_unlock_object(&msq->q_perm); + rcu_read_unlock(); + + return msq->q_perm.id; +} + +static inline bool msg_fits_inqueue(struct msg_queue *msq, size_t msgsz) +{ + return msgsz + msq->q_cbytes <= msq->q_qbytes && + 1 + msq->q_qnum <= msq->q_qbytes; +} + +static inline void ss_add(struct msg_queue *msq, + struct msg_sender *mss, size_t msgsz) +{ + mss->tsk = current; + mss->msgsz = msgsz; + /* + * No memory barrier required: we did ipc_lock_object(), + * and the waker obtains that lock before calling wake_q_add(). + */ + __set_current_state(TASK_INTERRUPTIBLE); + list_add_tail(&mss->list, &msq->q_senders); +} + +static inline void ss_del(struct msg_sender *mss) +{ + if (mss->list.next) + list_del(&mss->list); +} + +static void ss_wakeup(struct msg_queue *msq, + struct wake_q_head *wake_q, bool kill) +{ + struct msg_sender *mss, *t; + struct task_struct *stop_tsk = NULL; + struct list_head *h = &msq->q_senders; + + list_for_each_entry_safe(mss, t, h, list) { + if (kill) + mss->list.next = NULL; + + /* + * Stop at the first task we don't wakeup, + * we've already iterated the original + * sender queue. + */ + else if (stop_tsk == mss->tsk) + break; + /* + * We are not in an EIDRM scenario here, therefore + * verify that we really need to wakeup the task. + * To maintain current semantics and wakeup order, + * move the sender to the tail on behalf of the + * blocked task. + */ + else if (!msg_fits_inqueue(msq, mss->msgsz)) { + if (!stop_tsk) + stop_tsk = mss->tsk; + + list_move_tail(&mss->list, &msq->q_senders); + continue; + } + + wake_q_add(wake_q, mss->tsk); + } +} + +static void expunge_all(struct msg_queue *msq, int res, + struct wake_q_head *wake_q) +{ + struct msg_receiver *msr, *t; + + list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { + struct task_struct *r_tsk; + + r_tsk = get_task_struct(msr->r_tsk); + + /* see MSG_BARRIER for purpose/pairing */ + smp_store_release(&msr->r_msg, ERR_PTR(res)); + wake_q_add_safe(wake_q, r_tsk); + } +} + +/* + * freeque() wakes up waiters on the sender and receiver waiting queue, + * removes the message queue from message queue ID IDR, and cleans up all the + * messages associated with this queue. + * + * msg_ids.rwsem (writer) and the spinlock for this message queue are held + * before freeque() is called. msg_ids.rwsem remains locked on exit. + */ +static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) + __releases(RCU) + __releases(&msq->q_perm) +{ + struct msg_msg *msg, *t; + struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm); + DEFINE_WAKE_Q(wake_q); + + expunge_all(msq, -EIDRM, &wake_q); + ss_wakeup(msq, &wake_q, true); + msg_rmid(ns, msq); + ipc_unlock_object(&msq->q_perm); + wake_up_q(&wake_q); + rcu_read_unlock(); + + list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) { + percpu_counter_sub_local(&ns->percpu_msg_hdrs, 1); + free_msg(msg); + } + percpu_counter_sub_local(&ns->percpu_msg_bytes, msq->q_cbytes); + ipc_update_pid(&msq->q_lspid, NULL); + ipc_update_pid(&msq->q_lrpid, NULL); + ipc_rcu_putref(&msq->q_perm, msg_rcu_free); +} + +long ksys_msgget(key_t key, int msgflg) +{ + struct ipc_namespace *ns; + static const struct ipc_ops msg_ops = { + .getnew = newque, + .associate = security_msg_queue_associate, + }; + struct ipc_params msg_params; + + ns = current->nsproxy->ipc_ns; + + msg_params.key = key; + msg_params.flg = msgflg; + + return ipcget(ns, &msg_ids(ns), &msg_ops, &msg_params); +} + +SYSCALL_DEFINE2(msgget, key_t, key, int, msgflg) +{ + return ksys_msgget(key, msgflg); +} + +static inline unsigned long +copy_msqid_to_user(void __user *buf, struct msqid64_ds *in, int version) +{ + switch (version) { + case IPC_64: + return copy_to_user(buf, in, sizeof(*in)); + case IPC_OLD: + { + struct msqid_ds out; + + memset(&out, 0, sizeof(out)); + + ipc64_perm_to_ipc_perm(&in->msg_perm, &out.msg_perm); + + out.msg_stime = in->msg_stime; + out.msg_rtime = in->msg_rtime; + out.msg_ctime = in->msg_ctime; + + if (in->msg_cbytes > USHRT_MAX) + out.msg_cbytes = USHRT_MAX; + else + out.msg_cbytes = in->msg_cbytes; + out.msg_lcbytes = in->msg_cbytes; + + if (in->msg_qnum > USHRT_MAX) + out.msg_qnum = USHRT_MAX; + else + out.msg_qnum = in->msg_qnum; + + if (in->msg_qbytes > USHRT_MAX) + out.msg_qbytes = USHRT_MAX; + else + out.msg_qbytes = in->msg_qbytes; + out.msg_lqbytes = in->msg_qbytes; + + out.msg_lspid = in->msg_lspid; + out.msg_lrpid = in->msg_lrpid; + + return copy_to_user(buf, &out, sizeof(out)); + } + default: + return -EINVAL; + } +} + +static inline unsigned long +copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version) +{ + switch (version) { + case IPC_64: + if (copy_from_user(out, buf, sizeof(*out))) + return -EFAULT; + return 0; + case IPC_OLD: + { + struct msqid_ds tbuf_old; + + if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) + return -EFAULT; + + out->msg_perm.uid = tbuf_old.msg_perm.uid; + out->msg_perm.gid = tbuf_old.msg_perm.gid; + out->msg_perm.mode = tbuf_old.msg_perm.mode; + + if (tbuf_old.msg_qbytes == 0) + out->msg_qbytes = tbuf_old.msg_lqbytes; + else + out->msg_qbytes = tbuf_old.msg_qbytes; + + return 0; + } + default: + return -EINVAL; + } +} + +/* + * This function handles some msgctl commands which require the rwsem + * to be held in write mode. + * NOTE: no locks must be held, the rwsem is taken inside this function. + */ +static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd, + struct ipc64_perm *perm, int msg_qbytes) +{ + struct kern_ipc_perm *ipcp; + struct msg_queue *msq; + int err; + + down_write(&msg_ids(ns).rwsem); + rcu_read_lock(); + + ipcp = ipcctl_obtain_check(ns, &msg_ids(ns), msqid, cmd, + perm, msg_qbytes); + if (IS_ERR(ipcp)) { + err = PTR_ERR(ipcp); + goto out_unlock1; + } + + msq = container_of(ipcp, struct msg_queue, q_perm); + + err = security_msg_queue_msgctl(&msq->q_perm, cmd); + if (err) + goto out_unlock1; + + switch (cmd) { + case IPC_RMID: + ipc_lock_object(&msq->q_perm); + /* freeque unlocks the ipc object and rcu */ + freeque(ns, ipcp); + goto out_up; + case IPC_SET: + { + DEFINE_WAKE_Q(wake_q); + + if (msg_qbytes > ns->msg_ctlmnb && + !capable(CAP_SYS_RESOURCE)) { + err = -EPERM; + goto out_unlock1; + } + + ipc_lock_object(&msq->q_perm); + err = ipc_update_perm(perm, ipcp); + if (err) + goto out_unlock0; + + msq->q_qbytes = msg_qbytes; + + msq->q_ctime = ktime_get_real_seconds(); + /* + * Sleeping receivers might be excluded by + * stricter permissions. + */ + expunge_all(msq, -EAGAIN, &wake_q); + /* + * Sleeping senders might be able to send + * due to a larger queue size. + */ + ss_wakeup(msq, &wake_q, false); + ipc_unlock_object(&msq->q_perm); + wake_up_q(&wake_q); + + goto out_unlock1; + } + default: + err = -EINVAL; + goto out_unlock1; + } + +out_unlock0: + ipc_unlock_object(&msq->q_perm); +out_unlock1: + rcu_read_unlock(); +out_up: + up_write(&msg_ids(ns).rwsem); + return err; +} + +static int msgctl_info(struct ipc_namespace *ns, int msqid, + int cmd, struct msginfo *msginfo) +{ + int err; + int max_idx; + + /* + * We must not return kernel stack data. + * due to padding, it's not enough + * to set all member fields. + */ + err = security_msg_queue_msgctl(NULL, cmd); + if (err) + return err; + + memset(msginfo, 0, sizeof(*msginfo)); + msginfo->msgmni = ns->msg_ctlmni; + msginfo->msgmax = ns->msg_ctlmax; + msginfo->msgmnb = ns->msg_ctlmnb; + msginfo->msgssz = MSGSSZ; + msginfo->msgseg = MSGSEG; + down_read(&msg_ids(ns).rwsem); + if (cmd == MSG_INFO) + msginfo->msgpool = msg_ids(ns).in_use; + max_idx = ipc_get_maxidx(&msg_ids(ns)); + up_read(&msg_ids(ns).rwsem); + if (cmd == MSG_INFO) { + msginfo->msgmap = min_t(int, + percpu_counter_sum(&ns->percpu_msg_hdrs), + INT_MAX); + msginfo->msgtql = min_t(int, + percpu_counter_sum(&ns->percpu_msg_bytes), + INT_MAX); + } else { + msginfo->msgmap = MSGMAP; + msginfo->msgpool = MSGPOOL; + msginfo->msgtql = MSGTQL; + } + return (max_idx < 0) ? 0 : max_idx; +} + +static int msgctl_stat(struct ipc_namespace *ns, int msqid, + int cmd, struct msqid64_ds *p) +{ + struct msg_queue *msq; + int err; + + memset(p, 0, sizeof(*p)); + + rcu_read_lock(); + if (cmd == MSG_STAT || cmd == MSG_STAT_ANY) { + msq = msq_obtain_object(ns, msqid); + if (IS_ERR(msq)) { + err = PTR_ERR(msq); + goto out_unlock; + } + } else { /* IPC_STAT */ + msq = msq_obtain_object_check(ns, msqid); + if (IS_ERR(msq)) { + err = PTR_ERR(msq); + goto out_unlock; + } + } + + /* see comment for SHM_STAT_ANY */ + if (cmd == MSG_STAT_ANY) + audit_ipc_obj(&msq->q_perm); + else { + err = -EACCES; + if (ipcperms(ns, &msq->q_perm, S_IRUGO)) + goto out_unlock; + } + + err = security_msg_queue_msgctl(&msq->q_perm, cmd); + if (err) + goto out_unlock; + + ipc_lock_object(&msq->q_perm); + + if (!ipc_valid_object(&msq->q_perm)) { + ipc_unlock_object(&msq->q_perm); + err = -EIDRM; + goto out_unlock; + } + + kernel_to_ipc64_perm(&msq->q_perm, &p->msg_perm); + p->msg_stime = msq->q_stime; + p->msg_rtime = msq->q_rtime; + p->msg_ctime = msq->q_ctime; +#ifndef CONFIG_64BIT + p->msg_stime_high = msq->q_stime >> 32; + p->msg_rtime_high = msq->q_rtime >> 32; + p->msg_ctime_high = msq->q_ctime >> 32; +#endif + p->msg_cbytes = msq->q_cbytes; + p->msg_qnum = msq->q_qnum; + p->msg_qbytes = msq->q_qbytes; + p->msg_lspid = pid_vnr(msq->q_lspid); + p->msg_lrpid = pid_vnr(msq->q_lrpid); + + if (cmd == IPC_STAT) { + /* + * As defined in SUS: + * Return 0 on success + */ + err = 0; + } else { + /* + * MSG_STAT and MSG_STAT_ANY (both Linux specific) + * Return the full id, including the sequence number + */ + err = msq->q_perm.id; + } + + ipc_unlock_object(&msq->q_perm); +out_unlock: + rcu_read_unlock(); + return err; +} + +static long ksys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf, int version) +{ + struct ipc_namespace *ns; + struct msqid64_ds msqid64; + int err; + + if (msqid < 0 || cmd < 0) + return -EINVAL; + + ns = current->nsproxy->ipc_ns; + + switch (cmd) { + case IPC_INFO: + case MSG_INFO: { + struct msginfo msginfo; + err = msgctl_info(ns, msqid, cmd, &msginfo); + if (err < 0) + return err; + if (copy_to_user(buf, &msginfo, sizeof(struct msginfo))) + err = -EFAULT; + return err; + } + case MSG_STAT: /* msqid is an index rather than a msg queue id */ + case MSG_STAT_ANY: + case IPC_STAT: + err = msgctl_stat(ns, msqid, cmd, &msqid64); + if (err < 0) + return err; + if (copy_msqid_to_user(buf, &msqid64, version)) + err = -EFAULT; + return err; + case IPC_SET: + if (copy_msqid_from_user(&msqid64, buf, version)) + return -EFAULT; + return msgctl_down(ns, msqid, cmd, &msqid64.msg_perm, + msqid64.msg_qbytes); + case IPC_RMID: + return msgctl_down(ns, msqid, cmd, NULL, 0); + default: + return -EINVAL; + } +} + +SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf) +{ + return ksys_msgctl(msqid, cmd, buf, IPC_64); +} + +#ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION +long ksys_old_msgctl(int msqid, int cmd, struct msqid_ds __user *buf) +{ + int version = ipc_parse_version(&cmd); + + return ksys_msgctl(msqid, cmd, buf, version); +} + +SYSCALL_DEFINE3(old_msgctl, int, msqid, int, cmd, struct msqid_ds __user *, buf) +{ + return ksys_old_msgctl(msqid, cmd, buf); +} +#endif + +#ifdef CONFIG_COMPAT + +struct compat_msqid_ds { + struct compat_ipc_perm msg_perm; + compat_uptr_t msg_first; + compat_uptr_t msg_last; + old_time32_t msg_stime; + old_time32_t msg_rtime; + old_time32_t msg_ctime; + compat_ulong_t msg_lcbytes; + compat_ulong_t msg_lqbytes; + unsigned short msg_cbytes; + unsigned short msg_qnum; + unsigned short msg_qbytes; + compat_ipc_pid_t msg_lspid; + compat_ipc_pid_t msg_lrpid; +}; + +static int copy_compat_msqid_from_user(struct msqid64_ds *out, void __user *buf, + int version) +{ + memset(out, 0, sizeof(*out)); + if (version == IPC_64) { + struct compat_msqid64_ds __user *p = buf; + if (get_compat_ipc64_perm(&out->msg_perm, &p->msg_perm)) + return -EFAULT; + if (get_user(out->msg_qbytes, &p->msg_qbytes)) + return -EFAULT; + } else { + struct compat_msqid_ds __user *p = buf; + if (get_compat_ipc_perm(&out->msg_perm, &p->msg_perm)) + return -EFAULT; + if (get_user(out->msg_qbytes, &p->msg_qbytes)) + return -EFAULT; + } + return 0; +} + +static int copy_compat_msqid_to_user(void __user *buf, struct msqid64_ds *in, + int version) +{ + if (version == IPC_64) { + struct compat_msqid64_ds v; + memset(&v, 0, sizeof(v)); + to_compat_ipc64_perm(&v.msg_perm, &in->msg_perm); + v.msg_stime = lower_32_bits(in->msg_stime); + v.msg_stime_high = upper_32_bits(in->msg_stime); + v.msg_rtime = lower_32_bits(in->msg_rtime); + v.msg_rtime_high = upper_32_bits(in->msg_rtime); + v.msg_ctime = lower_32_bits(in->msg_ctime); + v.msg_ctime_high = upper_32_bits(in->msg_ctime); + v.msg_cbytes = in->msg_cbytes; + v.msg_qnum = in->msg_qnum; + v.msg_qbytes = in->msg_qbytes; + v.msg_lspid = in->msg_lspid; + v.msg_lrpid = in->msg_lrpid; + return copy_to_user(buf, &v, sizeof(v)); + } else { + struct compat_msqid_ds v; + memset(&v, 0, sizeof(v)); + to_compat_ipc_perm(&v.msg_perm, &in->msg_perm); + v.msg_stime = in->msg_stime; + v.msg_rtime = in->msg_rtime; + v.msg_ctime = in->msg_ctime; + v.msg_cbytes = in->msg_cbytes; + v.msg_qnum = in->msg_qnum; + v.msg_qbytes = in->msg_qbytes; + v.msg_lspid = in->msg_lspid; + v.msg_lrpid = in->msg_lrpid; + return copy_to_user(buf, &v, sizeof(v)); + } +} + +static long compat_ksys_msgctl(int msqid, int cmd, void __user *uptr, int version) +{ + struct ipc_namespace *ns; + int err; + struct msqid64_ds msqid64; + + ns = current->nsproxy->ipc_ns; + + if (msqid < 0 || cmd < 0) + return -EINVAL; + + switch (cmd & (~IPC_64)) { + case IPC_INFO: + case MSG_INFO: { + struct msginfo msginfo; + err = msgctl_info(ns, msqid, cmd, &msginfo); + if (err < 0) + return err; + if (copy_to_user(uptr, &msginfo, sizeof(struct msginfo))) + err = -EFAULT; + return err; + } + case IPC_STAT: + case MSG_STAT: + case MSG_STAT_ANY: + err = msgctl_stat(ns, msqid, cmd, &msqid64); + if (err < 0) + return err; + if (copy_compat_msqid_to_user(uptr, &msqid64, version)) + err = -EFAULT; + return err; + case IPC_SET: + if (copy_compat_msqid_from_user(&msqid64, uptr, version)) + return -EFAULT; + return msgctl_down(ns, msqid, cmd, &msqid64.msg_perm, msqid64.msg_qbytes); + case IPC_RMID: + return msgctl_down(ns, msqid, cmd, NULL, 0); + default: + return -EINVAL; + } +} + +COMPAT_SYSCALL_DEFINE3(msgctl, int, msqid, int, cmd, void __user *, uptr) +{ + return compat_ksys_msgctl(msqid, cmd, uptr, IPC_64); +} + +#ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION +long compat_ksys_old_msgctl(int msqid, int cmd, void __user *uptr) +{ + int version = compat_ipc_parse_version(&cmd); + + return compat_ksys_msgctl(msqid, cmd, uptr, version); +} + +COMPAT_SYSCALL_DEFINE3(old_msgctl, int, msqid, int, cmd, void __user *, uptr) +{ + return compat_ksys_old_msgctl(msqid, cmd, uptr); +} +#endif +#endif + +static int testmsg(struct msg_msg *msg, long type, int mode) +{ + switch (mode) { + case SEARCH_ANY: + case SEARCH_NUMBER: + return 1; + case SEARCH_LESSEQUAL: + if (msg->m_type <= type) + return 1; + break; + case SEARCH_EQUAL: + if (msg->m_type == type) + return 1; + break; + case SEARCH_NOTEQUAL: + if (msg->m_type != type) + return 1; + break; + } + return 0; +} + +static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg, + struct wake_q_head *wake_q) +{ + struct msg_receiver *msr, *t; + + list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { + if (testmsg(msg, msr->r_msgtype, msr->r_mode) && + !security_msg_queue_msgrcv(&msq->q_perm, msg, msr->r_tsk, + msr->r_msgtype, msr->r_mode)) { + + list_del(&msr->r_list); + if (msr->r_maxsize < msg->m_ts) { + wake_q_add(wake_q, msr->r_tsk); + + /* See expunge_all regarding memory barrier */ + smp_store_release(&msr->r_msg, ERR_PTR(-E2BIG)); + } else { + ipc_update_pid(&msq->q_lrpid, task_pid(msr->r_tsk)); + msq->q_rtime = ktime_get_real_seconds(); + + wake_q_add(wake_q, msr->r_tsk); + + /* See expunge_all regarding memory barrier */ + smp_store_release(&msr->r_msg, msg); + return 1; + } + } + } + + return 0; +} + +static long do_msgsnd(int msqid, long mtype, void __user *mtext, + size_t msgsz, int msgflg) +{ + struct msg_queue *msq; + struct msg_msg *msg; + int err; + struct ipc_namespace *ns; + DEFINE_WAKE_Q(wake_q); + + ns = current->nsproxy->ipc_ns; + + if (msgsz > ns->msg_ctlmax || (long) msgsz < 0 || msqid < 0) + return -EINVAL; + if (mtype < 1) + return -EINVAL; + + msg = load_msg(mtext, msgsz); + if (IS_ERR(msg)) + return PTR_ERR(msg); + + msg->m_type = mtype; + msg->m_ts = msgsz; + + rcu_read_lock(); + msq = msq_obtain_object_check(ns, msqid); + if (IS_ERR(msq)) { + err = PTR_ERR(msq); + goto out_unlock1; + } + + ipc_lock_object(&msq->q_perm); + + for (;;) { + struct msg_sender s; + + err = -EACCES; + if (ipcperms(ns, &msq->q_perm, S_IWUGO)) + goto out_unlock0; + + /* raced with RMID? */ + if (!ipc_valid_object(&msq->q_perm)) { + err = -EIDRM; + goto out_unlock0; + } + + err = security_msg_queue_msgsnd(&msq->q_perm, msg, msgflg); + if (err) + goto out_unlock0; + + if (msg_fits_inqueue(msq, msgsz)) + break; + + /* queue full, wait: */ + if (msgflg & IPC_NOWAIT) { + err = -EAGAIN; + goto out_unlock0; + } + + /* enqueue the sender and prepare to block */ + ss_add(msq, &s, msgsz); + + if (!ipc_rcu_getref(&msq->q_perm)) { + err = -EIDRM; + goto out_unlock0; + } + + ipc_unlock_object(&msq->q_perm); + rcu_read_unlock(); + schedule(); + + rcu_read_lock(); + ipc_lock_object(&msq->q_perm); + + ipc_rcu_putref(&msq->q_perm, msg_rcu_free); + /* raced with RMID? */ + if (!ipc_valid_object(&msq->q_perm)) { + err = -EIDRM; + goto out_unlock0; + } + ss_del(&s); + + if (signal_pending(current)) { + err = -ERESTARTNOHAND; + goto out_unlock0; + } + + } + + ipc_update_pid(&msq->q_lspid, task_tgid(current)); + msq->q_stime = ktime_get_real_seconds(); + + if (!pipelined_send(msq, msg, &wake_q)) { + /* no one is waiting for this message, enqueue it */ + list_add_tail(&msg->m_list, &msq->q_messages); + msq->q_cbytes += msgsz; + msq->q_qnum++; + percpu_counter_add_local(&ns->percpu_msg_bytes, msgsz); + percpu_counter_add_local(&ns->percpu_msg_hdrs, 1); + } + + err = 0; + msg = NULL; + +out_unlock0: + ipc_unlock_object(&msq->q_perm); + wake_up_q(&wake_q); +out_unlock1: + rcu_read_unlock(); + if (msg != NULL) + free_msg(msg); + return err; +} + +long ksys_msgsnd(int msqid, struct msgbuf __user *msgp, size_t msgsz, + int msgflg) +{ + long mtype; + + if (get_user(mtype, &msgp->mtype)) + return -EFAULT; + return do_msgsnd(msqid, mtype, msgp->mtext, msgsz, msgflg); +} + +SYSCALL_DEFINE4(msgsnd, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz, + int, msgflg) +{ + return ksys_msgsnd(msqid, msgp, msgsz, msgflg); +} + +#ifdef CONFIG_COMPAT + +struct compat_msgbuf { + compat_long_t mtype; + char mtext[1]; +}; + +long compat_ksys_msgsnd(int msqid, compat_uptr_t msgp, + compat_ssize_t msgsz, int msgflg) +{ + struct compat_msgbuf __user *up = compat_ptr(msgp); + compat_long_t mtype; + + if (get_user(mtype, &up->mtype)) + return -EFAULT; + return do_msgsnd(msqid, mtype, up->mtext, (ssize_t)msgsz, msgflg); +} + +COMPAT_SYSCALL_DEFINE4(msgsnd, int, msqid, compat_uptr_t, msgp, + compat_ssize_t, msgsz, int, msgflg) +{ + return compat_ksys_msgsnd(msqid, msgp, msgsz, msgflg); +} +#endif + +static inline int convert_mode(long *msgtyp, int msgflg) +{ + if (msgflg & MSG_COPY) + return SEARCH_NUMBER; + /* + * find message of correct type. + * msgtyp = 0 => get first. + * msgtyp > 0 => get first message of matching type. + * msgtyp < 0 => get message with least type must be < abs(msgtype). + */ + if (*msgtyp == 0) + return SEARCH_ANY; + if (*msgtyp < 0) { + if (*msgtyp == LONG_MIN) /* -LONG_MIN is undefined */ + *msgtyp = LONG_MAX; + else + *msgtyp = -*msgtyp; + return SEARCH_LESSEQUAL; + } + if (msgflg & MSG_EXCEPT) + return SEARCH_NOTEQUAL; + return SEARCH_EQUAL; +} + +static long do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz) +{ + struct msgbuf __user *msgp = dest; + size_t msgsz; + + if (put_user(msg->m_type, &msgp->mtype)) + return -EFAULT; + + msgsz = (bufsz > msg->m_ts) ? msg->m_ts : bufsz; + if (store_msg(msgp->mtext, msg, msgsz)) + return -EFAULT; + return msgsz; +} + +#ifdef CONFIG_CHECKPOINT_RESTORE +/* + * This function creates new kernel message structure, large enough to store + * bufsz message bytes. + */ +static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz) +{ + struct msg_msg *copy; + + /* + * Create dummy message to copy real message to. + */ + copy = load_msg(buf, bufsz); + if (!IS_ERR(copy)) + copy->m_ts = bufsz; + return copy; +} + +static inline void free_copy(struct msg_msg *copy) +{ + if (copy) + free_msg(copy); +} +#else +static inline struct msg_msg *prepare_copy(void __user *buf, size_t bufsz) +{ + return ERR_PTR(-ENOSYS); +} + +static inline void free_copy(struct msg_msg *copy) +{ +} +#endif + +static struct msg_msg *find_msg(struct msg_queue *msq, long *msgtyp, int mode) +{ + struct msg_msg *msg, *found = NULL; + long count = 0; + + list_for_each_entry(msg, &msq->q_messages, m_list) { + if (testmsg(msg, *msgtyp, mode) && + !security_msg_queue_msgrcv(&msq->q_perm, msg, current, + *msgtyp, mode)) { + if (mode == SEARCH_LESSEQUAL && msg->m_type != 1) { + *msgtyp = msg->m_type - 1; + found = msg; + } else if (mode == SEARCH_NUMBER) { + if (*msgtyp == count) + return msg; + } else + return msg; + count++; + } + } + + return found ?: ERR_PTR(-EAGAIN); +} + +static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgflg, + long (*msg_handler)(void __user *, struct msg_msg *, size_t)) +{ + int mode; + struct msg_queue *msq; + struct ipc_namespace *ns; + struct msg_msg *msg, *copy = NULL; + DEFINE_WAKE_Q(wake_q); + + ns = current->nsproxy->ipc_ns; + + if (msqid < 0 || (long) bufsz < 0) + return -EINVAL; + + if (msgflg & MSG_COPY) { + if ((msgflg & MSG_EXCEPT) || !(msgflg & IPC_NOWAIT)) + return -EINVAL; + copy = prepare_copy(buf, min_t(size_t, bufsz, ns->msg_ctlmax)); + if (IS_ERR(copy)) + return PTR_ERR(copy); + } + mode = convert_mode(&msgtyp, msgflg); + + rcu_read_lock(); + msq = msq_obtain_object_check(ns, msqid); + if (IS_ERR(msq)) { + rcu_read_unlock(); + free_copy(copy); + return PTR_ERR(msq); + } + + for (;;) { + struct msg_receiver msr_d; + + msg = ERR_PTR(-EACCES); + if (ipcperms(ns, &msq->q_perm, S_IRUGO)) + goto out_unlock1; + + ipc_lock_object(&msq->q_perm); + + /* raced with RMID? */ + if (!ipc_valid_object(&msq->q_perm)) { + msg = ERR_PTR(-EIDRM); + goto out_unlock0; + } + + msg = find_msg(msq, &msgtyp, mode); + if (!IS_ERR(msg)) { + /* + * Found a suitable message. + * Unlink it from the queue. + */ + if ((bufsz < msg->m_ts) && !(msgflg & MSG_NOERROR)) { + msg = ERR_PTR(-E2BIG); + goto out_unlock0; + } + /* + * If we are copying, then do not unlink message and do + * not update queue parameters. + */ + if (msgflg & MSG_COPY) { + msg = copy_msg(msg, copy); + goto out_unlock0; + } + + list_del(&msg->m_list); + msq->q_qnum--; + msq->q_rtime = ktime_get_real_seconds(); + ipc_update_pid(&msq->q_lrpid, task_tgid(current)); + msq->q_cbytes -= msg->m_ts; + percpu_counter_sub_local(&ns->percpu_msg_bytes, msg->m_ts); + percpu_counter_sub_local(&ns->percpu_msg_hdrs, 1); + ss_wakeup(msq, &wake_q, false); + + goto out_unlock0; + } + + /* No message waiting. Wait for a message */ + if (msgflg & IPC_NOWAIT) { + msg = ERR_PTR(-ENOMSG); + goto out_unlock0; + } + + list_add_tail(&msr_d.r_list, &msq->q_receivers); + msr_d.r_tsk = current; + msr_d.r_msgtype = msgtyp; + msr_d.r_mode = mode; + if (msgflg & MSG_NOERROR) + msr_d.r_maxsize = INT_MAX; + else + msr_d.r_maxsize = bufsz; + + /* memory barrier not require due to ipc_lock_object() */ + WRITE_ONCE(msr_d.r_msg, ERR_PTR(-EAGAIN)); + + /* memory barrier not required, we own ipc_lock_object() */ + __set_current_state(TASK_INTERRUPTIBLE); + + ipc_unlock_object(&msq->q_perm); + rcu_read_unlock(); + schedule(); + + /* + * Lockless receive, part 1: + * We don't hold a reference to the queue and getting a + * reference would defeat the idea of a lockless operation, + * thus the code relies on rcu to guarantee the existence of + * msq: + * Prior to destruction, expunge_all(-EIRDM) changes r_msg. + * Thus if r_msg is -EAGAIN, then the queue not yet destroyed. + */ + rcu_read_lock(); + + /* + * Lockless receive, part 2: + * The work in pipelined_send() and expunge_all(): + * - Set pointer to message + * - Queue the receiver task for later wakeup + * - Wake up the process after the lock is dropped. + * + * Should the process wake up before this wakeup (due to a + * signal) it will either see the message and continue ... + */ + msg = READ_ONCE(msr_d.r_msg); + if (msg != ERR_PTR(-EAGAIN)) { + /* see MSG_BARRIER for purpose/pairing */ + smp_acquire__after_ctrl_dep(); + + goto out_unlock1; + } + + /* + * ... or see -EAGAIN, acquire the lock to check the message + * again. + */ + ipc_lock_object(&msq->q_perm); + + msg = READ_ONCE(msr_d.r_msg); + if (msg != ERR_PTR(-EAGAIN)) + goto out_unlock0; + + list_del(&msr_d.r_list); + if (signal_pending(current)) { + msg = ERR_PTR(-ERESTARTNOHAND); + goto out_unlock0; + } + + ipc_unlock_object(&msq->q_perm); + } + +out_unlock0: + ipc_unlock_object(&msq->q_perm); + wake_up_q(&wake_q); +out_unlock1: + rcu_read_unlock(); + if (IS_ERR(msg)) { + free_copy(copy); + return PTR_ERR(msg); + } + + bufsz = msg_handler(buf, msg, bufsz); + free_msg(msg); + + return bufsz; +} + +long ksys_msgrcv(int msqid, struct msgbuf __user *msgp, size_t msgsz, + long msgtyp, int msgflg) +{ + return do_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg, do_msg_fill); +} + +SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz, + long, msgtyp, int, msgflg) +{ + return ksys_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg); +} + +#ifdef CONFIG_COMPAT +static long compat_do_msg_fill(void __user *dest, struct msg_msg *msg, size_t bufsz) +{ + struct compat_msgbuf __user *msgp = dest; + size_t msgsz; + + if (put_user(msg->m_type, &msgp->mtype)) + return -EFAULT; + + msgsz = (bufsz > msg->m_ts) ? msg->m_ts : bufsz; + if (store_msg(msgp->mtext, msg, msgsz)) + return -EFAULT; + return msgsz; +} + +long compat_ksys_msgrcv(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, + compat_long_t msgtyp, int msgflg) +{ + return do_msgrcv(msqid, compat_ptr(msgp), (ssize_t)msgsz, (long)msgtyp, + msgflg, compat_do_msg_fill); +} + +COMPAT_SYSCALL_DEFINE5(msgrcv, int, msqid, compat_uptr_t, msgp, + compat_ssize_t, msgsz, compat_long_t, msgtyp, + int, msgflg) +{ + return compat_ksys_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg); +} +#endif + +int msg_init_ns(struct ipc_namespace *ns) +{ + int ret; + + ns->msg_ctlmax = MSGMAX; + ns->msg_ctlmnb = MSGMNB; + ns->msg_ctlmni = MSGMNI; + + ret = percpu_counter_init(&ns->percpu_msg_bytes, 0, GFP_KERNEL); + if (ret) + goto fail_msg_bytes; + ret = percpu_counter_init(&ns->percpu_msg_hdrs, 0, GFP_KERNEL); + if (ret) + goto fail_msg_hdrs; + ipc_init_ids(&ns->ids[IPC_MSG_IDS]); + return 0; + +fail_msg_hdrs: + percpu_counter_destroy(&ns->percpu_msg_bytes); +fail_msg_bytes: + return ret; +} + +#ifdef CONFIG_IPC_NS +void msg_exit_ns(struct ipc_namespace *ns) +{ + free_ipcs(ns, &msg_ids(ns), freeque); + idr_destroy(&ns->ids[IPC_MSG_IDS].ipcs_idr); + rhashtable_destroy(&ns->ids[IPC_MSG_IDS].key_ht); + percpu_counter_destroy(&ns->percpu_msg_bytes); + percpu_counter_destroy(&ns->percpu_msg_hdrs); +} +#endif + +#ifdef CONFIG_PROC_FS +static int sysvipc_msg_proc_show(struct seq_file *s, void *it) +{ + struct pid_namespace *pid_ns = ipc_seq_pid_ns(s); + struct user_namespace *user_ns = seq_user_ns(s); + struct kern_ipc_perm *ipcp = it; + struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm); + + seq_printf(s, + "%10d %10d %4o %10lu %10lu %5u %5u %5u %5u %5u %5u %10llu %10llu %10llu\n", + msq->q_perm.key, + msq->q_perm.id, + msq->q_perm.mode, + msq->q_cbytes, + msq->q_qnum, + pid_nr_ns(msq->q_lspid, pid_ns), + pid_nr_ns(msq->q_lrpid, pid_ns), + from_kuid_munged(user_ns, msq->q_perm.uid), + from_kgid_munged(user_ns, msq->q_perm.gid), + from_kuid_munged(user_ns, msq->q_perm.cuid), + from_kgid_munged(user_ns, msq->q_perm.cgid), + msq->q_stime, + msq->q_rtime, + msq->q_ctime); + + return 0; +} +#endif + +void __init msg_init(void) +{ + msg_init_ns(&init_ipc_ns); + + ipc_init_proc_interface("sysvipc/msg", + " key msqid perms cbytes qnum lspid lrpid uid gid cuid cgid stime rtime ctime\n", + IPC_MSG_IDS, sysvipc_msg_proc_show); +} diff --git a/ipc/msgutil.c b/ipc/msgutil.c new file mode 100644 index 0000000000..d0a0e877ca --- /dev/null +++ b/ipc/msgutil.c @@ -0,0 +1,184 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * linux/ipc/msgutil.c + * Copyright (C) 1999, 2004 Manfred Spraul + */ + +#include <linux/spinlock.h> +#include <linux/init.h> +#include <linux/security.h> +#include <linux/slab.h> +#include <linux/ipc.h> +#include <linux/msg.h> +#include <linux/ipc_namespace.h> +#include <linux/utsname.h> +#include <linux/proc_ns.h> +#include <linux/uaccess.h> +#include <linux/sched.h> + +#include "util.h" + +DEFINE_SPINLOCK(mq_lock); + +/* + * The next 2 defines are here bc this is the only file + * compiled when either CONFIG_SYSVIPC and CONFIG_POSIX_MQUEUE + * and not CONFIG_IPC_NS. + */ +struct ipc_namespace init_ipc_ns = { + .ns.count = REFCOUNT_INIT(1), + .user_ns = &init_user_ns, + .ns.inum = PROC_IPC_INIT_INO, +#ifdef CONFIG_IPC_NS + .ns.ops = &ipcns_operations, +#endif +}; + +struct msg_msgseg { + struct msg_msgseg *next; + /* the next part of the message follows immediately */ +}; + +#define DATALEN_MSG ((size_t)PAGE_SIZE-sizeof(struct msg_msg)) +#define DATALEN_SEG ((size_t)PAGE_SIZE-sizeof(struct msg_msgseg)) + + +static struct msg_msg *alloc_msg(size_t len) +{ + struct msg_msg *msg; + struct msg_msgseg **pseg; + size_t alen; + + alen = min(len, DATALEN_MSG); + msg = kmalloc(sizeof(*msg) + alen, GFP_KERNEL_ACCOUNT); + if (msg == NULL) + return NULL; + + msg->next = NULL; + msg->security = NULL; + + len -= alen; + pseg = &msg->next; + while (len > 0) { + struct msg_msgseg *seg; + + cond_resched(); + + alen = min(len, DATALEN_SEG); + seg = kmalloc(sizeof(*seg) + alen, GFP_KERNEL_ACCOUNT); + if (seg == NULL) + goto out_err; + *pseg = seg; + seg->next = NULL; + pseg = &seg->next; + len -= alen; + } + + return msg; + +out_err: + free_msg(msg); + return NULL; +} + +struct msg_msg *load_msg(const void __user *src, size_t len) +{ + struct msg_msg *msg; + struct msg_msgseg *seg; + int err = -EFAULT; + size_t alen; + + msg = alloc_msg(len); + if (msg == NULL) + return ERR_PTR(-ENOMEM); + + alen = min(len, DATALEN_MSG); + if (copy_from_user(msg + 1, src, alen)) + goto out_err; + + for (seg = msg->next; seg != NULL; seg = seg->next) { + len -= alen; + src = (char __user *)src + alen; + alen = min(len, DATALEN_SEG); + if (copy_from_user(seg + 1, src, alen)) + goto out_err; + } + + err = security_msg_msg_alloc(msg); + if (err) + goto out_err; + + return msg; + +out_err: + free_msg(msg); + return ERR_PTR(err); +} +#ifdef CONFIG_CHECKPOINT_RESTORE +struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst) +{ + struct msg_msgseg *dst_pseg, *src_pseg; + size_t len = src->m_ts; + size_t alen; + + if (src->m_ts > dst->m_ts) + return ERR_PTR(-EINVAL); + + alen = min(len, DATALEN_MSG); + memcpy(dst + 1, src + 1, alen); + + for (dst_pseg = dst->next, src_pseg = src->next; + src_pseg != NULL; + dst_pseg = dst_pseg->next, src_pseg = src_pseg->next) { + + len -= alen; + alen = min(len, DATALEN_SEG); + memcpy(dst_pseg + 1, src_pseg + 1, alen); + } + + dst->m_type = src->m_type; + dst->m_ts = src->m_ts; + + return dst; +} +#else +struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst) +{ + return ERR_PTR(-ENOSYS); +} +#endif +int store_msg(void __user *dest, struct msg_msg *msg, size_t len) +{ + size_t alen; + struct msg_msgseg *seg; + + alen = min(len, DATALEN_MSG); + if (copy_to_user(dest, msg + 1, alen)) + return -1; + + for (seg = msg->next; seg != NULL; seg = seg->next) { + len -= alen; + dest = (char __user *)dest + alen; + alen = min(len, DATALEN_SEG); + if (copy_to_user(dest, seg + 1, alen)) + return -1; + } + return 0; +} + +void free_msg(struct msg_msg *msg) +{ + struct msg_msgseg *seg; + + security_msg_msg_free(msg); + + seg = msg->next; + kfree(msg); + while (seg != NULL) { + struct msg_msgseg *tmp = seg->next; + + cond_resched(); + kfree(seg); + seg = tmp; + } +} diff --git a/ipc/namespace.c b/ipc/namespace.c new file mode 100644 index 0000000000..6ecc30effd --- /dev/null +++ b/ipc/namespace.c @@ -0,0 +1,258 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/ipc/namespace.c + * Copyright (C) 2006 Pavel Emelyanov <xemul@openvz.org> OpenVZ, SWsoft Inc. + */ + +#include <linux/ipc.h> +#include <linux/msg.h> +#include <linux/ipc_namespace.h> +#include <linux/rcupdate.h> +#include <linux/nsproxy.h> +#include <linux/slab.h> +#include <linux/cred.h> +#include <linux/fs.h> +#include <linux/mount.h> +#include <linux/user_namespace.h> +#include <linux/proc_ns.h> +#include <linux/sched/task.h> + +#include "util.h" + +/* + * The work queue is used to avoid the cost of synchronize_rcu in kern_unmount. + */ +static void free_ipc(struct work_struct *unused); +static DECLARE_WORK(free_ipc_work, free_ipc); + +static struct ucounts *inc_ipc_namespaces(struct user_namespace *ns) +{ + return inc_ucount(ns, current_euid(), UCOUNT_IPC_NAMESPACES); +} + +static void dec_ipc_namespaces(struct ucounts *ucounts) +{ + dec_ucount(ucounts, UCOUNT_IPC_NAMESPACES); +} + +static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns, + struct ipc_namespace *old_ns) +{ + struct ipc_namespace *ns; + struct ucounts *ucounts; + int err; + + err = -ENOSPC; + again: + ucounts = inc_ipc_namespaces(user_ns); + if (!ucounts) { + /* + * IPC namespaces are freed asynchronously, by free_ipc_work. + * If frees were pending, flush_work will wait, and + * return true. Fail the allocation if no frees are pending. + */ + if (flush_work(&free_ipc_work)) + goto again; + goto fail; + } + + err = -ENOMEM; + ns = kzalloc(sizeof(struct ipc_namespace), GFP_KERNEL_ACCOUNT); + if (ns == NULL) + goto fail_dec; + + err = ns_alloc_inum(&ns->ns); + if (err) + goto fail_free; + ns->ns.ops = &ipcns_operations; + + refcount_set(&ns->ns.count, 1); + ns->user_ns = get_user_ns(user_ns); + ns->ucounts = ucounts; + + err = mq_init_ns(ns); + if (err) + goto fail_put; + + err = -ENOMEM; + if (!setup_mq_sysctls(ns)) + goto fail_put; + + if (!setup_ipc_sysctls(ns)) + goto fail_mq; + + err = msg_init_ns(ns); + if (err) + goto fail_put; + + sem_init_ns(ns); + shm_init_ns(ns); + + return ns; + +fail_mq: + retire_mq_sysctls(ns); + +fail_put: + put_user_ns(ns->user_ns); + ns_free_inum(&ns->ns); +fail_free: + kfree(ns); +fail_dec: + dec_ipc_namespaces(ucounts); +fail: + return ERR_PTR(err); +} + +struct ipc_namespace *copy_ipcs(unsigned long flags, + struct user_namespace *user_ns, struct ipc_namespace *ns) +{ + if (!(flags & CLONE_NEWIPC)) + return get_ipc_ns(ns); + return create_ipc_ns(user_ns, ns); +} + +/* + * free_ipcs - free all ipcs of one type + * @ns: the namespace to remove the ipcs from + * @ids: the table of ipcs to free + * @free: the function called to free each individual ipc + * + * Called for each kind of ipc when an ipc_namespace exits. + */ +void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids, + void (*free)(struct ipc_namespace *, struct kern_ipc_perm *)) +{ + struct kern_ipc_perm *perm; + int next_id; + int total, in_use; + + down_write(&ids->rwsem); + + in_use = ids->in_use; + + for (total = 0, next_id = 0; total < in_use; next_id++) { + perm = idr_find(&ids->ipcs_idr, next_id); + if (perm == NULL) + continue; + rcu_read_lock(); + ipc_lock_object(perm); + free(ns, perm); + total++; + } + up_write(&ids->rwsem); +} + +static void free_ipc_ns(struct ipc_namespace *ns) +{ + /* + * Caller needs to wait for an RCU grace period to have passed + * after making the mount point inaccessible to new accesses. + */ + mntput(ns->mq_mnt); + sem_exit_ns(ns); + msg_exit_ns(ns); + shm_exit_ns(ns); + + retire_mq_sysctls(ns); + retire_ipc_sysctls(ns); + + dec_ipc_namespaces(ns->ucounts); + put_user_ns(ns->user_ns); + ns_free_inum(&ns->ns); + kfree(ns); +} + +static LLIST_HEAD(free_ipc_list); +static void free_ipc(struct work_struct *unused) +{ + struct llist_node *node = llist_del_all(&free_ipc_list); + struct ipc_namespace *n, *t; + + llist_for_each_entry_safe(n, t, node, mnt_llist) + mnt_make_shortterm(n->mq_mnt); + + /* Wait for any last users to have gone away. */ + synchronize_rcu(); + + llist_for_each_entry_safe(n, t, node, mnt_llist) + free_ipc_ns(n); +} + +/* + * put_ipc_ns - drop a reference to an ipc namespace. + * @ns: the namespace to put + * + * If this is the last task in the namespace exiting, and + * it is dropping the refcount to 0, then it can race with + * a task in another ipc namespace but in a mounts namespace + * which has this ipcns's mqueuefs mounted, doing some action + * with one of the mqueuefs files. That can raise the refcount. + * So dropping the refcount, and raising the refcount when + * accessing it through the VFS, are protected with mq_lock. + * + * (Clearly, a task raising the refcount on its own ipc_ns + * needn't take mq_lock since it can't race with the last task + * in the ipcns exiting). + */ +void put_ipc_ns(struct ipc_namespace *ns) +{ + if (refcount_dec_and_lock(&ns->ns.count, &mq_lock)) { + mq_clear_sbinfo(ns); + spin_unlock(&mq_lock); + + if (llist_add(&ns->mnt_llist, &free_ipc_list)) + schedule_work(&free_ipc_work); + } +} + +static inline struct ipc_namespace *to_ipc_ns(struct ns_common *ns) +{ + return container_of(ns, struct ipc_namespace, ns); +} + +static struct ns_common *ipcns_get(struct task_struct *task) +{ + struct ipc_namespace *ns = NULL; + struct nsproxy *nsproxy; + + task_lock(task); + nsproxy = task->nsproxy; + if (nsproxy) + ns = get_ipc_ns(nsproxy->ipc_ns); + task_unlock(task); + + return ns ? &ns->ns : NULL; +} + +static void ipcns_put(struct ns_common *ns) +{ + return put_ipc_ns(to_ipc_ns(ns)); +} + +static int ipcns_install(struct nsset *nsset, struct ns_common *new) +{ + struct nsproxy *nsproxy = nsset->nsproxy; + struct ipc_namespace *ns = to_ipc_ns(new); + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) || + !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + put_ipc_ns(nsproxy->ipc_ns); + nsproxy->ipc_ns = get_ipc_ns(ns); + return 0; +} + +static struct user_namespace *ipcns_owner(struct ns_common *ns) +{ + return to_ipc_ns(ns)->user_ns; +} + +const struct proc_ns_operations ipcns_operations = { + .name = "ipc", + .type = CLONE_NEWIPC, + .get = ipcns_get, + .put = ipcns_put, + .install = ipcns_install, + .owner = ipcns_owner, +}; diff --git a/ipc/sem.c b/ipc/sem.c new file mode 100644 index 0000000000..a39cdc7bf8 --- /dev/null +++ b/ipc/sem.c @@ -0,0 +1,2484 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/ipc/sem.c + * Copyright (C) 1992 Krishna Balasubramanian + * Copyright (C) 1995 Eric Schenk, Bruno Haible + * + * /proc/sysvipc/sem support (c) 1999 Dragos Acostachioaie <dragos@iname.com> + * + * SMP-threaded, sysctl's added + * (c) 1999 Manfred Spraul <manfred@colorfullife.com> + * Enforced range limit on SEM_UNDO + * (c) 2001 Red Hat Inc + * Lockless wakeup + * (c) 2003 Manfred Spraul <manfred@colorfullife.com> + * (c) 2016 Davidlohr Bueso <dave@stgolabs.net> + * Further wakeup optimizations, documentation + * (c) 2010 Manfred Spraul <manfred@colorfullife.com> + * + * support for audit of ipc object properties and permission changes + * Dustin Kirkland <dustin.kirkland@us.ibm.com> + * + * namespaces support + * OpenVZ, SWsoft Inc. + * Pavel Emelianov <xemul@openvz.org> + * + * Implementation notes: (May 2010) + * This file implements System V semaphores. + * + * User space visible behavior: + * - FIFO ordering for semop() operations (just FIFO, not starvation + * protection) + * - multiple semaphore operations that alter the same semaphore in + * one semop() are handled. + * - sem_ctime (time of last semctl()) is updated in the IPC_SET, SETVAL and + * SETALL calls. + * - two Linux specific semctl() commands: SEM_STAT, SEM_INFO. + * - undo adjustments at process exit are limited to 0..SEMVMX. + * - namespace are supported. + * - SEMMSL, SEMMNS, SEMOPM and SEMMNI can be configured at runtime by writing + * to /proc/sys/kernel/sem. + * - statistics about the usage are reported in /proc/sysvipc/sem. + * + * Internals: + * - scalability: + * - all global variables are read-mostly. + * - semop() calls and semctl(RMID) are synchronized by RCU. + * - most operations do write operations (actually: spin_lock calls) to + * the per-semaphore array structure. + * Thus: Perfect SMP scaling between independent semaphore arrays. + * If multiple semaphores in one array are used, then cache line + * trashing on the semaphore array spinlock will limit the scaling. + * - semncnt and semzcnt are calculated on demand in count_semcnt() + * - the task that performs a successful semop() scans the list of all + * sleeping tasks and completes any pending operations that can be fulfilled. + * Semaphores are actively given to waiting tasks (necessary for FIFO). + * (see update_queue()) + * - To improve the scalability, the actual wake-up calls are performed after + * dropping all locks. (see wake_up_sem_queue_prepare()) + * - All work is done by the waker, the woken up task does not have to do + * anything - not even acquiring a lock or dropping a refcount. + * - A woken up task may not even touch the semaphore array anymore, it may + * have been destroyed already by a semctl(RMID). + * - UNDO values are stored in an array (one per process and per + * semaphore array, lazily allocated). For backwards compatibility, multiple + * modes for the UNDO variables are supported (per process, per thread) + * (see copy_semundo, CLONE_SYSVSEM) + * - There are two lists of the pending operations: a per-array list + * and per-semaphore list (stored in the array). This allows to achieve FIFO + * ordering without always scanning all pending operations. + * The worst-case behavior is nevertheless O(N^2) for N wakeups. + */ + +#include <linux/compat.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/init.h> +#include <linux/proc_fs.h> +#include <linux/time.h> +#include <linux/security.h> +#include <linux/syscalls.h> +#include <linux/audit.h> +#include <linux/capability.h> +#include <linux/seq_file.h> +#include <linux/rwsem.h> +#include <linux/nsproxy.h> +#include <linux/ipc_namespace.h> +#include <linux/sched/wake_q.h> +#include <linux/nospec.h> +#include <linux/rhashtable.h> + +#include <linux/uaccess.h> +#include "util.h" + +/* One semaphore structure for each semaphore in the system. */ +struct sem { + int semval; /* current value */ + /* + * PID of the process that last modified the semaphore. For + * Linux, specifically these are: + * - semop + * - semctl, via SETVAL and SETALL. + * - at task exit when performing undo adjustments (see exit_sem). + */ + struct pid *sempid; + spinlock_t lock; /* spinlock for fine-grained semtimedop */ + struct list_head pending_alter; /* pending single-sop operations */ + /* that alter the semaphore */ + struct list_head pending_const; /* pending single-sop operations */ + /* that do not alter the semaphore*/ + time64_t sem_otime; /* candidate for sem_otime */ +} ____cacheline_aligned_in_smp; + +/* One sem_array data structure for each set of semaphores in the system. */ +struct sem_array { + struct kern_ipc_perm sem_perm; /* permissions .. see ipc.h */ + time64_t sem_ctime; /* create/last semctl() time */ + struct list_head pending_alter; /* pending operations */ + /* that alter the array */ + struct list_head pending_const; /* pending complex operations */ + /* that do not alter semvals */ + struct list_head list_id; /* undo requests on this array */ + int sem_nsems; /* no. of semaphores in array */ + int complex_count; /* pending complex operations */ + unsigned int use_global_lock;/* >0: global lock required */ + + struct sem sems[]; +} __randomize_layout; + +/* One queue for each sleeping process in the system. */ +struct sem_queue { + struct list_head list; /* queue of pending operations */ + struct task_struct *sleeper; /* this process */ + struct sem_undo *undo; /* undo structure */ + struct pid *pid; /* process id of requesting process */ + int status; /* completion status of operation */ + struct sembuf *sops; /* array of pending operations */ + struct sembuf *blocking; /* the operation that blocked */ + int nsops; /* number of operations */ + bool alter; /* does *sops alter the array? */ + bool dupsop; /* sops on more than one sem_num */ +}; + +/* Each task has a list of undo requests. They are executed automatically + * when the process exits. + */ +struct sem_undo { + struct list_head list_proc; /* per-process list: * + * all undos from one process + * rcu protected */ + struct rcu_head rcu; /* rcu struct for sem_undo */ + struct sem_undo_list *ulp; /* back ptr to sem_undo_list */ + struct list_head list_id; /* per semaphore array list: + * all undos for one array */ + int semid; /* semaphore set identifier */ + short semadj[]; /* array of adjustments */ + /* one per semaphore */ +}; + +/* sem_undo_list controls shared access to the list of sem_undo structures + * that may be shared among all a CLONE_SYSVSEM task group. + */ +struct sem_undo_list { + refcount_t refcnt; + spinlock_t lock; + struct list_head list_proc; +}; + + +#define sem_ids(ns) ((ns)->ids[IPC_SEM_IDS]) + +static int newary(struct ipc_namespace *, struct ipc_params *); +static void freeary(struct ipc_namespace *, struct kern_ipc_perm *); +#ifdef CONFIG_PROC_FS +static int sysvipc_sem_proc_show(struct seq_file *s, void *it); +#endif + +#define SEMMSL_FAST 256 /* 512 bytes on stack */ +#define SEMOPM_FAST 64 /* ~ 372 bytes on stack */ + +/* + * Switching from the mode suitable for simple ops + * to the mode for complex ops is costly. Therefore: + * use some hysteresis + */ +#define USE_GLOBAL_LOCK_HYSTERESIS 10 + +/* + * Locking: + * a) global sem_lock() for read/write + * sem_undo.id_next, + * sem_array.complex_count, + * sem_array.pending{_alter,_const}, + * sem_array.sem_undo + * + * b) global or semaphore sem_lock() for read/write: + * sem_array.sems[i].pending_{const,alter}: + * + * c) special: + * sem_undo_list.list_proc: + * * undo_list->lock for write + * * rcu for read + * use_global_lock: + * * global sem_lock() for write + * * either local or global sem_lock() for read. + * + * Memory ordering: + * Most ordering is enforced by using spin_lock() and spin_unlock(). + * + * Exceptions: + * 1) use_global_lock: (SEM_BARRIER_1) + * Setting it from non-zero to 0 is a RELEASE, this is ensured by + * using smp_store_release(): Immediately after setting it to 0, + * a simple op can start. + * Testing if it is non-zero is an ACQUIRE, this is ensured by using + * smp_load_acquire(). + * Setting it from 0 to non-zero must be ordered with regards to + * this smp_load_acquire(), this is guaranteed because the smp_load_acquire() + * is inside a spin_lock() and after a write from 0 to non-zero a + * spin_lock()+spin_unlock() is done. + * To prevent the compiler/cpu temporarily writing 0 to use_global_lock, + * READ_ONCE()/WRITE_ONCE() is used. + * + * 2) queue.status: (SEM_BARRIER_2) + * Initialization is done while holding sem_lock(), so no further barrier is + * required. + * Setting it to a result code is a RELEASE, this is ensured by both a + * smp_store_release() (for case a) and while holding sem_lock() + * (for case b). + * The ACQUIRE when reading the result code without holding sem_lock() is + * achieved by using READ_ONCE() + smp_acquire__after_ctrl_dep(). + * (case a above). + * Reading the result code while holding sem_lock() needs no further barriers, + * the locks inside sem_lock() enforce ordering (case b above) + * + * 3) current->state: + * current->state is set to TASK_INTERRUPTIBLE while holding sem_lock(). + * The wakeup is handled using the wake_q infrastructure. wake_q wakeups may + * happen immediately after calling wake_q_add. As wake_q_add_safe() is called + * when holding sem_lock(), no further barriers are required. + * + * See also ipc/mqueue.c for more details on the covered races. + */ + +#define sc_semmsl sem_ctls[0] +#define sc_semmns sem_ctls[1] +#define sc_semopm sem_ctls[2] +#define sc_semmni sem_ctls[3] + +void sem_init_ns(struct ipc_namespace *ns) +{ + ns->sc_semmsl = SEMMSL; + ns->sc_semmns = SEMMNS; + ns->sc_semopm = SEMOPM; + ns->sc_semmni = SEMMNI; + ns->used_sems = 0; + ipc_init_ids(&ns->ids[IPC_SEM_IDS]); +} + +#ifdef CONFIG_IPC_NS +void sem_exit_ns(struct ipc_namespace *ns) +{ + free_ipcs(ns, &sem_ids(ns), freeary); + idr_destroy(&ns->ids[IPC_SEM_IDS].ipcs_idr); + rhashtable_destroy(&ns->ids[IPC_SEM_IDS].key_ht); +} +#endif + +void __init sem_init(void) +{ + sem_init_ns(&init_ipc_ns); + ipc_init_proc_interface("sysvipc/sem", + " key semid perms nsems uid gid cuid cgid otime ctime\n", + IPC_SEM_IDS, sysvipc_sem_proc_show); +} + +/** + * unmerge_queues - unmerge queues, if possible. + * @sma: semaphore array + * + * The function unmerges the wait queues if complex_count is 0. + * It must be called prior to dropping the global semaphore array lock. + */ +static void unmerge_queues(struct sem_array *sma) +{ + struct sem_queue *q, *tq; + + /* complex operations still around? */ + if (sma->complex_count) + return; + /* + * We will switch back to simple mode. + * Move all pending operation back into the per-semaphore + * queues. + */ + list_for_each_entry_safe(q, tq, &sma->pending_alter, list) { + struct sem *curr; + curr = &sma->sems[q->sops[0].sem_num]; + + list_add_tail(&q->list, &curr->pending_alter); + } + INIT_LIST_HEAD(&sma->pending_alter); +} + +/** + * merge_queues - merge single semop queues into global queue + * @sma: semaphore array + * + * This function merges all per-semaphore queues into the global queue. + * It is necessary to achieve FIFO ordering for the pending single-sop + * operations when a multi-semop operation must sleep. + * Only the alter operations must be moved, the const operations can stay. + */ +static void merge_queues(struct sem_array *sma) +{ + int i; + for (i = 0; i < sma->sem_nsems; i++) { + struct sem *sem = &sma->sems[i]; + + list_splice_init(&sem->pending_alter, &sma->pending_alter); + } +} + +static void sem_rcu_free(struct rcu_head *head) +{ + struct kern_ipc_perm *p = container_of(head, struct kern_ipc_perm, rcu); + struct sem_array *sma = container_of(p, struct sem_array, sem_perm); + + security_sem_free(&sma->sem_perm); + kvfree(sma); +} + +/* + * Enter the mode suitable for non-simple operations: + * Caller must own sem_perm.lock. + */ +static void complexmode_enter(struct sem_array *sma) +{ + int i; + struct sem *sem; + + if (sma->use_global_lock > 0) { + /* + * We are already in global lock mode. + * Nothing to do, just reset the + * counter until we return to simple mode. + */ + WRITE_ONCE(sma->use_global_lock, USE_GLOBAL_LOCK_HYSTERESIS); + return; + } + WRITE_ONCE(sma->use_global_lock, USE_GLOBAL_LOCK_HYSTERESIS); + + for (i = 0; i < sma->sem_nsems; i++) { + sem = &sma->sems[i]; + spin_lock(&sem->lock); + spin_unlock(&sem->lock); + } +} + +/* + * Try to leave the mode that disallows simple operations: + * Caller must own sem_perm.lock. + */ +static void complexmode_tryleave(struct sem_array *sma) +{ + if (sma->complex_count) { + /* Complex ops are sleeping. + * We must stay in complex mode + */ + return; + } + if (sma->use_global_lock == 1) { + + /* See SEM_BARRIER_1 for purpose/pairing */ + smp_store_release(&sma->use_global_lock, 0); + } else { + WRITE_ONCE(sma->use_global_lock, + sma->use_global_lock-1); + } +} + +#define SEM_GLOBAL_LOCK (-1) +/* + * If the request contains only one semaphore operation, and there are + * no complex transactions pending, lock only the semaphore involved. + * Otherwise, lock the entire semaphore array, since we either have + * multiple semaphores in our own semops, or we need to look at + * semaphores from other pending complex operations. + */ +static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, + int nsops) +{ + struct sem *sem; + int idx; + + if (nsops != 1) { + /* Complex operation - acquire a full lock */ + ipc_lock_object(&sma->sem_perm); + + /* Prevent parallel simple ops */ + complexmode_enter(sma); + return SEM_GLOBAL_LOCK; + } + + /* + * Only one semaphore affected - try to optimize locking. + * Optimized locking is possible if no complex operation + * is either enqueued or processed right now. + * + * Both facts are tracked by use_global_mode. + */ + idx = array_index_nospec(sops->sem_num, sma->sem_nsems); + sem = &sma->sems[idx]; + + /* + * Initial check for use_global_lock. Just an optimization, + * no locking, no memory barrier. + */ + if (!READ_ONCE(sma->use_global_lock)) { + /* + * It appears that no complex operation is around. + * Acquire the per-semaphore lock. + */ + spin_lock(&sem->lock); + + /* see SEM_BARRIER_1 for purpose/pairing */ + if (!smp_load_acquire(&sma->use_global_lock)) { + /* fast path successful! */ + return sops->sem_num; + } + spin_unlock(&sem->lock); + } + + /* slow path: acquire the full lock */ + ipc_lock_object(&sma->sem_perm); + + if (sma->use_global_lock == 0) { + /* + * The use_global_lock mode ended while we waited for + * sma->sem_perm.lock. Thus we must switch to locking + * with sem->lock. + * Unlike in the fast path, there is no need to recheck + * sma->use_global_lock after we have acquired sem->lock: + * We own sma->sem_perm.lock, thus use_global_lock cannot + * change. + */ + spin_lock(&sem->lock); + + ipc_unlock_object(&sma->sem_perm); + return sops->sem_num; + } else { + /* + * Not a false alarm, thus continue to use the global lock + * mode. No need for complexmode_enter(), this was done by + * the caller that has set use_global_mode to non-zero. + */ + return SEM_GLOBAL_LOCK; + } +} + +static inline void sem_unlock(struct sem_array *sma, int locknum) +{ + if (locknum == SEM_GLOBAL_LOCK) { + unmerge_queues(sma); + complexmode_tryleave(sma); + ipc_unlock_object(&sma->sem_perm); + } else { + struct sem *sem = &sma->sems[locknum]; + spin_unlock(&sem->lock); + } +} + +/* + * sem_lock_(check_) routines are called in the paths where the rwsem + * is not held. + * + * The caller holds the RCU read lock. + */ +static inline struct sem_array *sem_obtain_object(struct ipc_namespace *ns, int id) +{ + struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&sem_ids(ns), id); + + if (IS_ERR(ipcp)) + return ERR_CAST(ipcp); + + return container_of(ipcp, struct sem_array, sem_perm); +} + +static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns, + int id) +{ + struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&sem_ids(ns), id); + + if (IS_ERR(ipcp)) + return ERR_CAST(ipcp); + + return container_of(ipcp, struct sem_array, sem_perm); +} + +static inline void sem_lock_and_putref(struct sem_array *sma) +{ + sem_lock(sma, NULL, -1); + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); +} + +static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s) +{ + ipc_rmid(&sem_ids(ns), &s->sem_perm); +} + +static struct sem_array *sem_alloc(size_t nsems) +{ + struct sem_array *sma; + + if (nsems > (INT_MAX - sizeof(*sma)) / sizeof(sma->sems[0])) + return NULL; + + sma = kvzalloc(struct_size(sma, sems, nsems), GFP_KERNEL_ACCOUNT); + if (unlikely(!sma)) + return NULL; + + return sma; +} + +/** + * newary - Create a new semaphore set + * @ns: namespace + * @params: ptr to the structure that contains key, semflg and nsems + * + * Called with sem_ids.rwsem held (as a writer) + */ +static int newary(struct ipc_namespace *ns, struct ipc_params *params) +{ + int retval; + struct sem_array *sma; + key_t key = params->key; + int nsems = params->u.nsems; + int semflg = params->flg; + int i; + + if (!nsems) + return -EINVAL; + if (ns->used_sems + nsems > ns->sc_semmns) + return -ENOSPC; + + sma = sem_alloc(nsems); + if (!sma) + return -ENOMEM; + + sma->sem_perm.mode = (semflg & S_IRWXUGO); + sma->sem_perm.key = key; + + sma->sem_perm.security = NULL; + retval = security_sem_alloc(&sma->sem_perm); + if (retval) { + kvfree(sma); + return retval; + } + + for (i = 0; i < nsems; i++) { + INIT_LIST_HEAD(&sma->sems[i].pending_alter); + INIT_LIST_HEAD(&sma->sems[i].pending_const); + spin_lock_init(&sma->sems[i].lock); + } + + sma->complex_count = 0; + sma->use_global_lock = USE_GLOBAL_LOCK_HYSTERESIS; + INIT_LIST_HEAD(&sma->pending_alter); + INIT_LIST_HEAD(&sma->pending_const); + INIT_LIST_HEAD(&sma->list_id); + sma->sem_nsems = nsems; + sma->sem_ctime = ktime_get_real_seconds(); + + /* ipc_addid() locks sma upon success. */ + retval = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni); + if (retval < 0) { + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); + return retval; + } + ns->used_sems += nsems; + + sem_unlock(sma, -1); + rcu_read_unlock(); + + return sma->sem_perm.id; +} + + +/* + * Called with sem_ids.rwsem and ipcp locked. + */ +static int sem_more_checks(struct kern_ipc_perm *ipcp, struct ipc_params *params) +{ + struct sem_array *sma; + + sma = container_of(ipcp, struct sem_array, sem_perm); + if (params->u.nsems > sma->sem_nsems) + return -EINVAL; + + return 0; +} + +long ksys_semget(key_t key, int nsems, int semflg) +{ + struct ipc_namespace *ns; + static const struct ipc_ops sem_ops = { + .getnew = newary, + .associate = security_sem_associate, + .more_checks = sem_more_checks, + }; + struct ipc_params sem_params; + + ns = current->nsproxy->ipc_ns; + + if (nsems < 0 || nsems > ns->sc_semmsl) + return -EINVAL; + + sem_params.key = key; + sem_params.flg = semflg; + sem_params.u.nsems = nsems; + + return ipcget(ns, &sem_ids(ns), &sem_ops, &sem_params); +} + +SYSCALL_DEFINE3(semget, key_t, key, int, nsems, int, semflg) +{ + return ksys_semget(key, nsems, semflg); +} + +/** + * perform_atomic_semop[_slow] - Attempt to perform semaphore + * operations on a given array. + * @sma: semaphore array + * @q: struct sem_queue that describes the operation + * + * Caller blocking are as follows, based the value + * indicated by the semaphore operation (sem_op): + * + * (1) >0 never blocks. + * (2) 0 (wait-for-zero operation): semval is non-zero. + * (3) <0 attempting to decrement semval to a value smaller than zero. + * + * Returns 0 if the operation was possible. + * Returns 1 if the operation is impossible, the caller must sleep. + * Returns <0 for error codes. + */ +static int perform_atomic_semop_slow(struct sem_array *sma, struct sem_queue *q) +{ + int result, sem_op, nsops; + struct pid *pid; + struct sembuf *sop; + struct sem *curr; + struct sembuf *sops; + struct sem_undo *un; + + sops = q->sops; + nsops = q->nsops; + un = q->undo; + + for (sop = sops; sop < sops + nsops; sop++) { + int idx = array_index_nospec(sop->sem_num, sma->sem_nsems); + curr = &sma->sems[idx]; + sem_op = sop->sem_op; + result = curr->semval; + + if (!sem_op && result) + goto would_block; + + result += sem_op; + if (result < 0) + goto would_block; + if (result > SEMVMX) + goto out_of_range; + + if (sop->sem_flg & SEM_UNDO) { + int undo = un->semadj[sop->sem_num] - sem_op; + /* Exceeding the undo range is an error. */ + if (undo < (-SEMAEM - 1) || undo > SEMAEM) + goto out_of_range; + un->semadj[sop->sem_num] = undo; + } + + curr->semval = result; + } + + sop--; + pid = q->pid; + while (sop >= sops) { + ipc_update_pid(&sma->sems[sop->sem_num].sempid, pid); + sop--; + } + + return 0; + +out_of_range: + result = -ERANGE; + goto undo; + +would_block: + q->blocking = sop; + + if (sop->sem_flg & IPC_NOWAIT) + result = -EAGAIN; + else + result = 1; + +undo: + sop--; + while (sop >= sops) { + sem_op = sop->sem_op; + sma->sems[sop->sem_num].semval -= sem_op; + if (sop->sem_flg & SEM_UNDO) + un->semadj[sop->sem_num] += sem_op; + sop--; + } + + return result; +} + +static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q) +{ + int result, sem_op, nsops; + struct sembuf *sop; + struct sem *curr; + struct sembuf *sops; + struct sem_undo *un; + + sops = q->sops; + nsops = q->nsops; + un = q->undo; + + if (unlikely(q->dupsop)) + return perform_atomic_semop_slow(sma, q); + + /* + * We scan the semaphore set twice, first to ensure that the entire + * operation can succeed, therefore avoiding any pointless writes + * to shared memory and having to undo such changes in order to block + * until the operations can go through. + */ + for (sop = sops; sop < sops + nsops; sop++) { + int idx = array_index_nospec(sop->sem_num, sma->sem_nsems); + + curr = &sma->sems[idx]; + sem_op = sop->sem_op; + result = curr->semval; + + if (!sem_op && result) + goto would_block; /* wait-for-zero */ + + result += sem_op; + if (result < 0) + goto would_block; + + if (result > SEMVMX) + return -ERANGE; + + if (sop->sem_flg & SEM_UNDO) { + int undo = un->semadj[sop->sem_num] - sem_op; + + /* Exceeding the undo range is an error. */ + if (undo < (-SEMAEM - 1) || undo > SEMAEM) + return -ERANGE; + } + } + + for (sop = sops; sop < sops + nsops; sop++) { + curr = &sma->sems[sop->sem_num]; + sem_op = sop->sem_op; + + if (sop->sem_flg & SEM_UNDO) { + int undo = un->semadj[sop->sem_num] - sem_op; + + un->semadj[sop->sem_num] = undo; + } + curr->semval += sem_op; + ipc_update_pid(&curr->sempid, q->pid); + } + + return 0; + +would_block: + q->blocking = sop; + return sop->sem_flg & IPC_NOWAIT ? -EAGAIN : 1; +} + +static inline void wake_up_sem_queue_prepare(struct sem_queue *q, int error, + struct wake_q_head *wake_q) +{ + struct task_struct *sleeper; + + sleeper = get_task_struct(q->sleeper); + + /* see SEM_BARRIER_2 for purpose/pairing */ + smp_store_release(&q->status, error); + + wake_q_add_safe(wake_q, sleeper); +} + +static void unlink_queue(struct sem_array *sma, struct sem_queue *q) +{ + list_del(&q->list); + if (q->nsops > 1) + sma->complex_count--; +} + +/** check_restart(sma, q) + * @sma: semaphore array + * @q: the operation that just completed + * + * update_queue is O(N^2) when it restarts scanning the whole queue of + * waiting operations. Therefore this function checks if the restart is + * really necessary. It is called after a previously waiting operation + * modified the array. + * Note that wait-for-zero operations are handled without restart. + */ +static inline int check_restart(struct sem_array *sma, struct sem_queue *q) +{ + /* pending complex alter operations are too difficult to analyse */ + if (!list_empty(&sma->pending_alter)) + return 1; + + /* we were a sleeping complex operation. Too difficult */ + if (q->nsops > 1) + return 1; + + /* It is impossible that someone waits for the new value: + * - complex operations always restart. + * - wait-for-zero are handled separately. + * - q is a previously sleeping simple operation that + * altered the array. It must be a decrement, because + * simple increments never sleep. + * - If there are older (higher priority) decrements + * in the queue, then they have observed the original + * semval value and couldn't proceed. The operation + * decremented to value - thus they won't proceed either. + */ + return 0; +} + +/** + * wake_const_ops - wake up non-alter tasks + * @sma: semaphore array. + * @semnum: semaphore that was modified. + * @wake_q: lockless wake-queue head. + * + * wake_const_ops must be called after a semaphore in a semaphore array + * was set to 0. If complex const operations are pending, wake_const_ops must + * be called with semnum = -1, as well as with the number of each modified + * semaphore. + * The tasks that must be woken up are added to @wake_q. The return code + * is stored in q->pid. + * The function returns 1 if at least one operation was completed successfully. + */ +static int wake_const_ops(struct sem_array *sma, int semnum, + struct wake_q_head *wake_q) +{ + struct sem_queue *q, *tmp; + struct list_head *pending_list; + int semop_completed = 0; + + if (semnum == -1) + pending_list = &sma->pending_const; + else + pending_list = &sma->sems[semnum].pending_const; + + list_for_each_entry_safe(q, tmp, pending_list, list) { + int error = perform_atomic_semop(sma, q); + + if (error > 0) + continue; + /* operation completed, remove from queue & wakeup */ + unlink_queue(sma, q); + + wake_up_sem_queue_prepare(q, error, wake_q); + if (error == 0) + semop_completed = 1; + } + + return semop_completed; +} + +/** + * do_smart_wakeup_zero - wakeup all wait for zero tasks + * @sma: semaphore array + * @sops: operations that were performed + * @nsops: number of operations + * @wake_q: lockless wake-queue head + * + * Checks all required queue for wait-for-zero operations, based + * on the actual changes that were performed on the semaphore array. + * The function returns 1 if at least one operation was completed successfully. + */ +static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops, + int nsops, struct wake_q_head *wake_q) +{ + int i; + int semop_completed = 0; + int got_zero = 0; + + /* first: the per-semaphore queues, if known */ + if (sops) { + for (i = 0; i < nsops; i++) { + int num = sops[i].sem_num; + + if (sma->sems[num].semval == 0) { + got_zero = 1; + semop_completed |= wake_const_ops(sma, num, wake_q); + } + } + } else { + /* + * No sops means modified semaphores not known. + * Assume all were changed. + */ + for (i = 0; i < sma->sem_nsems; i++) { + if (sma->sems[i].semval == 0) { + got_zero = 1; + semop_completed |= wake_const_ops(sma, i, wake_q); + } + } + } + /* + * If one of the modified semaphores got 0, + * then check the global queue, too. + */ + if (got_zero) + semop_completed |= wake_const_ops(sma, -1, wake_q); + + return semop_completed; +} + + +/** + * update_queue - look for tasks that can be completed. + * @sma: semaphore array. + * @semnum: semaphore that was modified. + * @wake_q: lockless wake-queue head. + * + * update_queue must be called after a semaphore in a semaphore array + * was modified. If multiple semaphores were modified, update_queue must + * be called with semnum = -1, as well as with the number of each modified + * semaphore. + * The tasks that must be woken up are added to @wake_q. The return code + * is stored in q->pid. + * The function internally checks if const operations can now succeed. + * + * The function return 1 if at least one semop was completed successfully. + */ +static int update_queue(struct sem_array *sma, int semnum, struct wake_q_head *wake_q) +{ + struct sem_queue *q, *tmp; + struct list_head *pending_list; + int semop_completed = 0; + + if (semnum == -1) + pending_list = &sma->pending_alter; + else + pending_list = &sma->sems[semnum].pending_alter; + +again: + list_for_each_entry_safe(q, tmp, pending_list, list) { + int error, restart; + + /* If we are scanning the single sop, per-semaphore list of + * one semaphore and that semaphore is 0, then it is not + * necessary to scan further: simple increments + * that affect only one entry succeed immediately and cannot + * be in the per semaphore pending queue, and decrements + * cannot be successful if the value is already 0. + */ + if (semnum != -1 && sma->sems[semnum].semval == 0) + break; + + error = perform_atomic_semop(sma, q); + + /* Does q->sleeper still need to sleep? */ + if (error > 0) + continue; + + unlink_queue(sma, q); + + if (error) { + restart = 0; + } else { + semop_completed = 1; + do_smart_wakeup_zero(sma, q->sops, q->nsops, wake_q); + restart = check_restart(sma, q); + } + + wake_up_sem_queue_prepare(q, error, wake_q); + if (restart) + goto again; + } + return semop_completed; +} + +/** + * set_semotime - set sem_otime + * @sma: semaphore array + * @sops: operations that modified the array, may be NULL + * + * sem_otime is replicated to avoid cache line trashing. + * This function sets one instance to the current time. + */ +static void set_semotime(struct sem_array *sma, struct sembuf *sops) +{ + if (sops == NULL) { + sma->sems[0].sem_otime = ktime_get_real_seconds(); + } else { + sma->sems[sops[0].sem_num].sem_otime = + ktime_get_real_seconds(); + } +} + +/** + * do_smart_update - optimized update_queue + * @sma: semaphore array + * @sops: operations that were performed + * @nsops: number of operations + * @otime: force setting otime + * @wake_q: lockless wake-queue head + * + * do_smart_update() does the required calls to update_queue and wakeup_zero, + * based on the actual changes that were performed on the semaphore array. + * Note that the function does not do the actual wake-up: the caller is + * responsible for calling wake_up_q(). + * It is safe to perform this call after dropping all locks. + */ +static void do_smart_update(struct sem_array *sma, struct sembuf *sops, int nsops, + int otime, struct wake_q_head *wake_q) +{ + int i; + + otime |= do_smart_wakeup_zero(sma, sops, nsops, wake_q); + + if (!list_empty(&sma->pending_alter)) { + /* semaphore array uses the global queue - just process it. */ + otime |= update_queue(sma, -1, wake_q); + } else { + if (!sops) { + /* + * No sops, thus the modified semaphores are not + * known. Check all. + */ + for (i = 0; i < sma->sem_nsems; i++) + otime |= update_queue(sma, i, wake_q); + } else { + /* + * Check the semaphores that were increased: + * - No complex ops, thus all sleeping ops are + * decrease. + * - if we decreased the value, then any sleeping + * semaphore ops won't be able to run: If the + * previous value was too small, then the new + * value will be too small, too. + */ + for (i = 0; i < nsops; i++) { + if (sops[i].sem_op > 0) { + otime |= update_queue(sma, + sops[i].sem_num, wake_q); + } + } + } + } + if (otime) + set_semotime(sma, sops); +} + +/* + * check_qop: Test if a queued operation sleeps on the semaphore semnum + */ +static int check_qop(struct sem_array *sma, int semnum, struct sem_queue *q, + bool count_zero) +{ + struct sembuf *sop = q->blocking; + + /* + * Linux always (since 0.99.10) reported a task as sleeping on all + * semaphores. This violates SUS, therefore it was changed to the + * standard compliant behavior. + * Give the administrators a chance to notice that an application + * might misbehave because it relies on the Linux behavior. + */ + pr_info_once("semctl(GETNCNT/GETZCNT) is since 3.16 Single Unix Specification compliant.\n" + "The task %s (%d) triggered the difference, watch for misbehavior.\n", + current->comm, task_pid_nr(current)); + + if (sop->sem_num != semnum) + return 0; + + if (count_zero && sop->sem_op == 0) + return 1; + if (!count_zero && sop->sem_op < 0) + return 1; + + return 0; +} + +/* The following counts are associated to each semaphore: + * semncnt number of tasks waiting on semval being nonzero + * semzcnt number of tasks waiting on semval being zero + * + * Per definition, a task waits only on the semaphore of the first semop + * that cannot proceed, even if additional operation would block, too. + */ +static int count_semcnt(struct sem_array *sma, ushort semnum, + bool count_zero) +{ + struct list_head *l; + struct sem_queue *q; + int semcnt; + + semcnt = 0; + /* First: check the simple operations. They are easy to evaluate */ + if (count_zero) + l = &sma->sems[semnum].pending_const; + else + l = &sma->sems[semnum].pending_alter; + + list_for_each_entry(q, l, list) { + /* all task on a per-semaphore list sleep on exactly + * that semaphore + */ + semcnt++; + } + + /* Then: check the complex operations. */ + list_for_each_entry(q, &sma->pending_alter, list) { + semcnt += check_qop(sma, semnum, q, count_zero); + } + if (count_zero) { + list_for_each_entry(q, &sma->pending_const, list) { + semcnt += check_qop(sma, semnum, q, count_zero); + } + } + return semcnt; +} + +/* Free a semaphore set. freeary() is called with sem_ids.rwsem locked + * as a writer and the spinlock for this semaphore set hold. sem_ids.rwsem + * remains locked on exit. + */ +static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) +{ + struct sem_undo *un, *tu; + struct sem_queue *q, *tq; + struct sem_array *sma = container_of(ipcp, struct sem_array, sem_perm); + int i; + DEFINE_WAKE_Q(wake_q); + + /* Free the existing undo structures for this semaphore set. */ + ipc_assert_locked_object(&sma->sem_perm); + list_for_each_entry_safe(un, tu, &sma->list_id, list_id) { + list_del(&un->list_id); + spin_lock(&un->ulp->lock); + un->semid = -1; + list_del_rcu(&un->list_proc); + spin_unlock(&un->ulp->lock); + kvfree_rcu(un, rcu); + } + + /* Wake up all pending processes and let them fail with EIDRM. */ + list_for_each_entry_safe(q, tq, &sma->pending_const, list) { + unlink_queue(sma, q); + wake_up_sem_queue_prepare(q, -EIDRM, &wake_q); + } + + list_for_each_entry_safe(q, tq, &sma->pending_alter, list) { + unlink_queue(sma, q); + wake_up_sem_queue_prepare(q, -EIDRM, &wake_q); + } + for (i = 0; i < sma->sem_nsems; i++) { + struct sem *sem = &sma->sems[i]; + list_for_each_entry_safe(q, tq, &sem->pending_const, list) { + unlink_queue(sma, q); + wake_up_sem_queue_prepare(q, -EIDRM, &wake_q); + } + list_for_each_entry_safe(q, tq, &sem->pending_alter, list) { + unlink_queue(sma, q); + wake_up_sem_queue_prepare(q, -EIDRM, &wake_q); + } + ipc_update_pid(&sem->sempid, NULL); + } + + /* Remove the semaphore set from the IDR */ + sem_rmid(ns, sma); + sem_unlock(sma, -1); + rcu_read_unlock(); + + wake_up_q(&wake_q); + ns->used_sems -= sma->sem_nsems; + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); +} + +static unsigned long copy_semid_to_user(void __user *buf, struct semid64_ds *in, int version) +{ + switch (version) { + case IPC_64: + return copy_to_user(buf, in, sizeof(*in)); + case IPC_OLD: + { + struct semid_ds out; + + memset(&out, 0, sizeof(out)); + + ipc64_perm_to_ipc_perm(&in->sem_perm, &out.sem_perm); + + out.sem_otime = in->sem_otime; + out.sem_ctime = in->sem_ctime; + out.sem_nsems = in->sem_nsems; + + return copy_to_user(buf, &out, sizeof(out)); + } + default: + return -EINVAL; + } +} + +static time64_t get_semotime(struct sem_array *sma) +{ + int i; + time64_t res; + + res = sma->sems[0].sem_otime; + for (i = 1; i < sma->sem_nsems; i++) { + time64_t to = sma->sems[i].sem_otime; + + if (to > res) + res = to; + } + return res; +} + +static int semctl_stat(struct ipc_namespace *ns, int semid, + int cmd, struct semid64_ds *semid64) +{ + struct sem_array *sma; + time64_t semotime; + int err; + + memset(semid64, 0, sizeof(*semid64)); + + rcu_read_lock(); + if (cmd == SEM_STAT || cmd == SEM_STAT_ANY) { + sma = sem_obtain_object(ns, semid); + if (IS_ERR(sma)) { + err = PTR_ERR(sma); + goto out_unlock; + } + } else { /* IPC_STAT */ + sma = sem_obtain_object_check(ns, semid); + if (IS_ERR(sma)) { + err = PTR_ERR(sma); + goto out_unlock; + } + } + + /* see comment for SHM_STAT_ANY */ + if (cmd == SEM_STAT_ANY) + audit_ipc_obj(&sma->sem_perm); + else { + err = -EACCES; + if (ipcperms(ns, &sma->sem_perm, S_IRUGO)) + goto out_unlock; + } + + err = security_sem_semctl(&sma->sem_perm, cmd); + if (err) + goto out_unlock; + + ipc_lock_object(&sma->sem_perm); + + if (!ipc_valid_object(&sma->sem_perm)) { + ipc_unlock_object(&sma->sem_perm); + err = -EIDRM; + goto out_unlock; + } + + kernel_to_ipc64_perm(&sma->sem_perm, &semid64->sem_perm); + semotime = get_semotime(sma); + semid64->sem_otime = semotime; + semid64->sem_ctime = sma->sem_ctime; +#ifndef CONFIG_64BIT + semid64->sem_otime_high = semotime >> 32; + semid64->sem_ctime_high = sma->sem_ctime >> 32; +#endif + semid64->sem_nsems = sma->sem_nsems; + + if (cmd == IPC_STAT) { + /* + * As defined in SUS: + * Return 0 on success + */ + err = 0; + } else { + /* + * SEM_STAT and SEM_STAT_ANY (both Linux specific) + * Return the full id, including the sequence number + */ + err = sma->sem_perm.id; + } + ipc_unlock_object(&sma->sem_perm); +out_unlock: + rcu_read_unlock(); + return err; +} + +static int semctl_info(struct ipc_namespace *ns, int semid, + int cmd, void __user *p) +{ + struct seminfo seminfo; + int max_idx; + int err; + + err = security_sem_semctl(NULL, cmd); + if (err) + return err; + + memset(&seminfo, 0, sizeof(seminfo)); + seminfo.semmni = ns->sc_semmni; + seminfo.semmns = ns->sc_semmns; + seminfo.semmsl = ns->sc_semmsl; + seminfo.semopm = ns->sc_semopm; + seminfo.semvmx = SEMVMX; + seminfo.semmnu = SEMMNU; + seminfo.semmap = SEMMAP; + seminfo.semume = SEMUME; + down_read(&sem_ids(ns).rwsem); + if (cmd == SEM_INFO) { + seminfo.semusz = sem_ids(ns).in_use; + seminfo.semaem = ns->used_sems; + } else { + seminfo.semusz = SEMUSZ; + seminfo.semaem = SEMAEM; + } + max_idx = ipc_get_maxidx(&sem_ids(ns)); + up_read(&sem_ids(ns).rwsem); + if (copy_to_user(p, &seminfo, sizeof(struct seminfo))) + return -EFAULT; + return (max_idx < 0) ? 0 : max_idx; +} + +static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum, + int val) +{ + struct sem_undo *un; + struct sem_array *sma; + struct sem *curr; + int err; + DEFINE_WAKE_Q(wake_q); + + if (val > SEMVMX || val < 0) + return -ERANGE; + + rcu_read_lock(); + sma = sem_obtain_object_check(ns, semid); + if (IS_ERR(sma)) { + rcu_read_unlock(); + return PTR_ERR(sma); + } + + if (semnum < 0 || semnum >= sma->sem_nsems) { + rcu_read_unlock(); + return -EINVAL; + } + + + if (ipcperms(ns, &sma->sem_perm, S_IWUGO)) { + rcu_read_unlock(); + return -EACCES; + } + + err = security_sem_semctl(&sma->sem_perm, SETVAL); + if (err) { + rcu_read_unlock(); + return -EACCES; + } + + sem_lock(sma, NULL, -1); + + if (!ipc_valid_object(&sma->sem_perm)) { + sem_unlock(sma, -1); + rcu_read_unlock(); + return -EIDRM; + } + + semnum = array_index_nospec(semnum, sma->sem_nsems); + curr = &sma->sems[semnum]; + + ipc_assert_locked_object(&sma->sem_perm); + list_for_each_entry(un, &sma->list_id, list_id) + un->semadj[semnum] = 0; + + curr->semval = val; + ipc_update_pid(&curr->sempid, task_tgid(current)); + sma->sem_ctime = ktime_get_real_seconds(); + /* maybe some queued-up processes were waiting for this */ + do_smart_update(sma, NULL, 0, 0, &wake_q); + sem_unlock(sma, -1); + rcu_read_unlock(); + wake_up_q(&wake_q); + return 0; +} + +static int semctl_main(struct ipc_namespace *ns, int semid, int semnum, + int cmd, void __user *p) +{ + struct sem_array *sma; + struct sem *curr; + int err, nsems; + ushort fast_sem_io[SEMMSL_FAST]; + ushort *sem_io = fast_sem_io; + DEFINE_WAKE_Q(wake_q); + + rcu_read_lock(); + sma = sem_obtain_object_check(ns, semid); + if (IS_ERR(sma)) { + rcu_read_unlock(); + return PTR_ERR(sma); + } + + nsems = sma->sem_nsems; + + err = -EACCES; + if (ipcperms(ns, &sma->sem_perm, cmd == SETALL ? S_IWUGO : S_IRUGO)) + goto out_rcu_wakeup; + + err = security_sem_semctl(&sma->sem_perm, cmd); + if (err) + goto out_rcu_wakeup; + + switch (cmd) { + case GETALL: + { + ushort __user *array = p; + int i; + + sem_lock(sma, NULL, -1); + if (!ipc_valid_object(&sma->sem_perm)) { + err = -EIDRM; + goto out_unlock; + } + if (nsems > SEMMSL_FAST) { + if (!ipc_rcu_getref(&sma->sem_perm)) { + err = -EIDRM; + goto out_unlock; + } + sem_unlock(sma, -1); + rcu_read_unlock(); + sem_io = kvmalloc_array(nsems, sizeof(ushort), + GFP_KERNEL); + if (sem_io == NULL) { + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); + return -ENOMEM; + } + + rcu_read_lock(); + sem_lock_and_putref(sma); + if (!ipc_valid_object(&sma->sem_perm)) { + err = -EIDRM; + goto out_unlock; + } + } + for (i = 0; i < sma->sem_nsems; i++) + sem_io[i] = sma->sems[i].semval; + sem_unlock(sma, -1); + rcu_read_unlock(); + err = 0; + if (copy_to_user(array, sem_io, nsems*sizeof(ushort))) + err = -EFAULT; + goto out_free; + } + case SETALL: + { + int i; + struct sem_undo *un; + + if (!ipc_rcu_getref(&sma->sem_perm)) { + err = -EIDRM; + goto out_rcu_wakeup; + } + rcu_read_unlock(); + + if (nsems > SEMMSL_FAST) { + sem_io = kvmalloc_array(nsems, sizeof(ushort), + GFP_KERNEL); + if (sem_io == NULL) { + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); + return -ENOMEM; + } + } + + if (copy_from_user(sem_io, p, nsems*sizeof(ushort))) { + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); + err = -EFAULT; + goto out_free; + } + + for (i = 0; i < nsems; i++) { + if (sem_io[i] > SEMVMX) { + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); + err = -ERANGE; + goto out_free; + } + } + rcu_read_lock(); + sem_lock_and_putref(sma); + if (!ipc_valid_object(&sma->sem_perm)) { + err = -EIDRM; + goto out_unlock; + } + + for (i = 0; i < nsems; i++) { + sma->sems[i].semval = sem_io[i]; + ipc_update_pid(&sma->sems[i].sempid, task_tgid(current)); + } + + ipc_assert_locked_object(&sma->sem_perm); + list_for_each_entry(un, &sma->list_id, list_id) { + for (i = 0; i < nsems; i++) + un->semadj[i] = 0; + } + sma->sem_ctime = ktime_get_real_seconds(); + /* maybe some queued-up processes were waiting for this */ + do_smart_update(sma, NULL, 0, 0, &wake_q); + err = 0; + goto out_unlock; + } + /* GETVAL, GETPID, GETNCTN, GETZCNT: fall-through */ + } + err = -EINVAL; + if (semnum < 0 || semnum >= nsems) + goto out_rcu_wakeup; + + sem_lock(sma, NULL, -1); + if (!ipc_valid_object(&sma->sem_perm)) { + err = -EIDRM; + goto out_unlock; + } + + semnum = array_index_nospec(semnum, nsems); + curr = &sma->sems[semnum]; + + switch (cmd) { + case GETVAL: + err = curr->semval; + goto out_unlock; + case GETPID: + err = pid_vnr(curr->sempid); + goto out_unlock; + case GETNCNT: + err = count_semcnt(sma, semnum, 0); + goto out_unlock; + case GETZCNT: + err = count_semcnt(sma, semnum, 1); + goto out_unlock; + } + +out_unlock: + sem_unlock(sma, -1); +out_rcu_wakeup: + rcu_read_unlock(); + wake_up_q(&wake_q); +out_free: + if (sem_io != fast_sem_io) + kvfree(sem_io); + return err; +} + +static inline unsigned long +copy_semid_from_user(struct semid64_ds *out, void __user *buf, int version) +{ + switch (version) { + case IPC_64: + if (copy_from_user(out, buf, sizeof(*out))) + return -EFAULT; + return 0; + case IPC_OLD: + { + struct semid_ds tbuf_old; + + if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) + return -EFAULT; + + out->sem_perm.uid = tbuf_old.sem_perm.uid; + out->sem_perm.gid = tbuf_old.sem_perm.gid; + out->sem_perm.mode = tbuf_old.sem_perm.mode; + + return 0; + } + default: + return -EINVAL; + } +} + +/* + * This function handles some semctl commands which require the rwsem + * to be held in write mode. + * NOTE: no locks must be held, the rwsem is taken inside this function. + */ +static int semctl_down(struct ipc_namespace *ns, int semid, + int cmd, struct semid64_ds *semid64) +{ + struct sem_array *sma; + int err; + struct kern_ipc_perm *ipcp; + + down_write(&sem_ids(ns).rwsem); + rcu_read_lock(); + + ipcp = ipcctl_obtain_check(ns, &sem_ids(ns), semid, cmd, + &semid64->sem_perm, 0); + if (IS_ERR(ipcp)) { + err = PTR_ERR(ipcp); + goto out_unlock1; + } + + sma = container_of(ipcp, struct sem_array, sem_perm); + + err = security_sem_semctl(&sma->sem_perm, cmd); + if (err) + goto out_unlock1; + + switch (cmd) { + case IPC_RMID: + sem_lock(sma, NULL, -1); + /* freeary unlocks the ipc object and rcu */ + freeary(ns, ipcp); + goto out_up; + case IPC_SET: + sem_lock(sma, NULL, -1); + err = ipc_update_perm(&semid64->sem_perm, ipcp); + if (err) + goto out_unlock0; + sma->sem_ctime = ktime_get_real_seconds(); + break; + default: + err = -EINVAL; + goto out_unlock1; + } + +out_unlock0: + sem_unlock(sma, -1); +out_unlock1: + rcu_read_unlock(); +out_up: + up_write(&sem_ids(ns).rwsem); + return err; +} + +static long ksys_semctl(int semid, int semnum, int cmd, unsigned long arg, int version) +{ + struct ipc_namespace *ns; + void __user *p = (void __user *)arg; + struct semid64_ds semid64; + int err; + + if (semid < 0) + return -EINVAL; + + ns = current->nsproxy->ipc_ns; + + switch (cmd) { + case IPC_INFO: + case SEM_INFO: + return semctl_info(ns, semid, cmd, p); + case IPC_STAT: + case SEM_STAT: + case SEM_STAT_ANY: + err = semctl_stat(ns, semid, cmd, &semid64); + if (err < 0) + return err; + if (copy_semid_to_user(p, &semid64, version)) + err = -EFAULT; + return err; + case GETALL: + case GETVAL: + case GETPID: + case GETNCNT: + case GETZCNT: + case SETALL: + return semctl_main(ns, semid, semnum, cmd, p); + case SETVAL: { + int val; +#if defined(CONFIG_64BIT) && defined(__BIG_ENDIAN) + /* big-endian 64bit */ + val = arg >> 32; +#else + /* 32bit or little-endian 64bit */ + val = arg; +#endif + return semctl_setval(ns, semid, semnum, val); + } + case IPC_SET: + if (copy_semid_from_user(&semid64, p, version)) + return -EFAULT; + fallthrough; + case IPC_RMID: + return semctl_down(ns, semid, cmd, &semid64); + default: + return -EINVAL; + } +} + +SYSCALL_DEFINE4(semctl, int, semid, int, semnum, int, cmd, unsigned long, arg) +{ + return ksys_semctl(semid, semnum, cmd, arg, IPC_64); +} + +#ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION +long ksys_old_semctl(int semid, int semnum, int cmd, unsigned long arg) +{ + int version = ipc_parse_version(&cmd); + + return ksys_semctl(semid, semnum, cmd, arg, version); +} + +SYSCALL_DEFINE4(old_semctl, int, semid, int, semnum, int, cmd, unsigned long, arg) +{ + return ksys_old_semctl(semid, semnum, cmd, arg); +} +#endif + +#ifdef CONFIG_COMPAT + +struct compat_semid_ds { + struct compat_ipc_perm sem_perm; + old_time32_t sem_otime; + old_time32_t sem_ctime; + compat_uptr_t sem_base; + compat_uptr_t sem_pending; + compat_uptr_t sem_pending_last; + compat_uptr_t undo; + unsigned short sem_nsems; +}; + +static int copy_compat_semid_from_user(struct semid64_ds *out, void __user *buf, + int version) +{ + memset(out, 0, sizeof(*out)); + if (version == IPC_64) { + struct compat_semid64_ds __user *p = buf; + return get_compat_ipc64_perm(&out->sem_perm, &p->sem_perm); + } else { + struct compat_semid_ds __user *p = buf; + return get_compat_ipc_perm(&out->sem_perm, &p->sem_perm); + } +} + +static int copy_compat_semid_to_user(void __user *buf, struct semid64_ds *in, + int version) +{ + if (version == IPC_64) { + struct compat_semid64_ds v; + memset(&v, 0, sizeof(v)); + to_compat_ipc64_perm(&v.sem_perm, &in->sem_perm); + v.sem_otime = lower_32_bits(in->sem_otime); + v.sem_otime_high = upper_32_bits(in->sem_otime); + v.sem_ctime = lower_32_bits(in->sem_ctime); + v.sem_ctime_high = upper_32_bits(in->sem_ctime); + v.sem_nsems = in->sem_nsems; + return copy_to_user(buf, &v, sizeof(v)); + } else { + struct compat_semid_ds v; + memset(&v, 0, sizeof(v)); + to_compat_ipc_perm(&v.sem_perm, &in->sem_perm); + v.sem_otime = in->sem_otime; + v.sem_ctime = in->sem_ctime; + v.sem_nsems = in->sem_nsems; + return copy_to_user(buf, &v, sizeof(v)); + } +} + +static long compat_ksys_semctl(int semid, int semnum, int cmd, int arg, int version) +{ + void __user *p = compat_ptr(arg); + struct ipc_namespace *ns; + struct semid64_ds semid64; + int err; + + ns = current->nsproxy->ipc_ns; + + if (semid < 0) + return -EINVAL; + + switch (cmd & (~IPC_64)) { + case IPC_INFO: + case SEM_INFO: + return semctl_info(ns, semid, cmd, p); + case IPC_STAT: + case SEM_STAT: + case SEM_STAT_ANY: + err = semctl_stat(ns, semid, cmd, &semid64); + if (err < 0) + return err; + if (copy_compat_semid_to_user(p, &semid64, version)) + err = -EFAULT; + return err; + case GETVAL: + case GETPID: + case GETNCNT: + case GETZCNT: + case GETALL: + case SETALL: + return semctl_main(ns, semid, semnum, cmd, p); + case SETVAL: + return semctl_setval(ns, semid, semnum, arg); + case IPC_SET: + if (copy_compat_semid_from_user(&semid64, p, version)) + return -EFAULT; + fallthrough; + case IPC_RMID: + return semctl_down(ns, semid, cmd, &semid64); + default: + return -EINVAL; + } +} + +COMPAT_SYSCALL_DEFINE4(semctl, int, semid, int, semnum, int, cmd, int, arg) +{ + return compat_ksys_semctl(semid, semnum, cmd, arg, IPC_64); +} + +#ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION +long compat_ksys_old_semctl(int semid, int semnum, int cmd, int arg) +{ + int version = compat_ipc_parse_version(&cmd); + + return compat_ksys_semctl(semid, semnum, cmd, arg, version); +} + +COMPAT_SYSCALL_DEFINE4(old_semctl, int, semid, int, semnum, int, cmd, int, arg) +{ + return compat_ksys_old_semctl(semid, semnum, cmd, arg); +} +#endif +#endif + +/* If the task doesn't already have a undo_list, then allocate one + * here. We guarantee there is only one thread using this undo list, + * and current is THE ONE + * + * If this allocation and assignment succeeds, but later + * portions of this code fail, there is no need to free the sem_undo_list. + * Just let it stay associated with the task, and it'll be freed later + * at exit time. + * + * This can block, so callers must hold no locks. + */ +static inline int get_undo_list(struct sem_undo_list **undo_listp) +{ + struct sem_undo_list *undo_list; + + undo_list = current->sysvsem.undo_list; + if (!undo_list) { + undo_list = kzalloc(sizeof(*undo_list), GFP_KERNEL_ACCOUNT); + if (undo_list == NULL) + return -ENOMEM; + spin_lock_init(&undo_list->lock); + refcount_set(&undo_list->refcnt, 1); + INIT_LIST_HEAD(&undo_list->list_proc); + + current->sysvsem.undo_list = undo_list; + } + *undo_listp = undo_list; + return 0; +} + +static struct sem_undo *__lookup_undo(struct sem_undo_list *ulp, int semid) +{ + struct sem_undo *un; + + list_for_each_entry_rcu(un, &ulp->list_proc, list_proc, + spin_is_locked(&ulp->lock)) { + if (un->semid == semid) + return un; + } + return NULL; +} + +static struct sem_undo *lookup_undo(struct sem_undo_list *ulp, int semid) +{ + struct sem_undo *un; + + assert_spin_locked(&ulp->lock); + + un = __lookup_undo(ulp, semid); + if (un) { + list_del_rcu(&un->list_proc); + list_add_rcu(&un->list_proc, &ulp->list_proc); + } + return un; +} + +/** + * find_alloc_undo - lookup (and if not present create) undo array + * @ns: namespace + * @semid: semaphore array id + * + * The function looks up (and if not present creates) the undo structure. + * The size of the undo structure depends on the size of the semaphore + * array, thus the alloc path is not that straightforward. + * Lifetime-rules: sem_undo is rcu-protected, on success, the function + * performs a rcu_read_lock(). + */ +static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) +{ + struct sem_array *sma; + struct sem_undo_list *ulp; + struct sem_undo *un, *new; + int nsems, error; + + error = get_undo_list(&ulp); + if (error) + return ERR_PTR(error); + + rcu_read_lock(); + spin_lock(&ulp->lock); + un = lookup_undo(ulp, semid); + spin_unlock(&ulp->lock); + if (likely(un != NULL)) + goto out; + + /* no undo structure around - allocate one. */ + /* step 1: figure out the size of the semaphore array */ + sma = sem_obtain_object_check(ns, semid); + if (IS_ERR(sma)) { + rcu_read_unlock(); + return ERR_CAST(sma); + } + + nsems = sma->sem_nsems; + if (!ipc_rcu_getref(&sma->sem_perm)) { + rcu_read_unlock(); + un = ERR_PTR(-EIDRM); + goto out; + } + rcu_read_unlock(); + + /* step 2: allocate new undo structure */ + new = kvzalloc(struct_size(new, semadj, nsems), GFP_KERNEL_ACCOUNT); + if (!new) { + ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); + return ERR_PTR(-ENOMEM); + } + + /* step 3: Acquire the lock on semaphore array */ + rcu_read_lock(); + sem_lock_and_putref(sma); + if (!ipc_valid_object(&sma->sem_perm)) { + sem_unlock(sma, -1); + rcu_read_unlock(); + kvfree(new); + un = ERR_PTR(-EIDRM); + goto out; + } + spin_lock(&ulp->lock); + + /* + * step 4: check for races: did someone else allocate the undo struct? + */ + un = lookup_undo(ulp, semid); + if (un) { + spin_unlock(&ulp->lock); + kvfree(new); + goto success; + } + /* step 5: initialize & link new undo structure */ + new->ulp = ulp; + new->semid = semid; + assert_spin_locked(&ulp->lock); + list_add_rcu(&new->list_proc, &ulp->list_proc); + ipc_assert_locked_object(&sma->sem_perm); + list_add(&new->list_id, &sma->list_id); + un = new; + spin_unlock(&ulp->lock); +success: + sem_unlock(sma, -1); +out: + return un; +} + +long __do_semtimedop(int semid, struct sembuf *sops, + unsigned nsops, const struct timespec64 *timeout, + struct ipc_namespace *ns) +{ + int error = -EINVAL; + struct sem_array *sma; + struct sembuf *sop; + struct sem_undo *un; + int max, locknum; + bool undos = false, alter = false, dupsop = false; + struct sem_queue queue; + unsigned long dup = 0; + ktime_t expires, *exp = NULL; + bool timed_out = false; + + if (nsops < 1 || semid < 0) + return -EINVAL; + if (nsops > ns->sc_semopm) + return -E2BIG; + + if (timeout) { + if (!timespec64_valid(timeout)) + return -EINVAL; + expires = ktime_add_safe(ktime_get(), + timespec64_to_ktime(*timeout)); + exp = &expires; + } + + + max = 0; + for (sop = sops; sop < sops + nsops; sop++) { + unsigned long mask = 1ULL << ((sop->sem_num) % BITS_PER_LONG); + + if (sop->sem_num >= max) + max = sop->sem_num; + if (sop->sem_flg & SEM_UNDO) + undos = true; + if (dup & mask) { + /* + * There was a previous alter access that appears + * to have accessed the same semaphore, thus use + * the dupsop logic. "appears", because the detection + * can only check % BITS_PER_LONG. + */ + dupsop = true; + } + if (sop->sem_op != 0) { + alter = true; + dup |= mask; + } + } + + if (undos) { + /* On success, find_alloc_undo takes the rcu_read_lock */ + un = find_alloc_undo(ns, semid); + if (IS_ERR(un)) { + error = PTR_ERR(un); + goto out; + } + } else { + un = NULL; + rcu_read_lock(); + } + + sma = sem_obtain_object_check(ns, semid); + if (IS_ERR(sma)) { + rcu_read_unlock(); + error = PTR_ERR(sma); + goto out; + } + + error = -EFBIG; + if (max >= sma->sem_nsems) { + rcu_read_unlock(); + goto out; + } + + error = -EACCES; + if (ipcperms(ns, &sma->sem_perm, alter ? S_IWUGO : S_IRUGO)) { + rcu_read_unlock(); + goto out; + } + + error = security_sem_semop(&sma->sem_perm, sops, nsops, alter); + if (error) { + rcu_read_unlock(); + goto out; + } + + error = -EIDRM; + locknum = sem_lock(sma, sops, nsops); + /* + * We eventually might perform the following check in a lockless + * fashion, considering ipc_valid_object() locking constraints. + * If nsops == 1 and there is no contention for sem_perm.lock, then + * only a per-semaphore lock is held and it's OK to proceed with the + * check below. More details on the fine grained locking scheme + * entangled here and why it's RMID race safe on comments at sem_lock() + */ + if (!ipc_valid_object(&sma->sem_perm)) + goto out_unlock; + /* + * semid identifiers are not unique - find_alloc_undo may have + * allocated an undo structure, it was invalidated by an RMID + * and now a new array with received the same id. Check and fail. + * This case can be detected checking un->semid. The existence of + * "un" itself is guaranteed by rcu. + */ + if (un && un->semid == -1) + goto out_unlock; + + queue.sops = sops; + queue.nsops = nsops; + queue.undo = un; + queue.pid = task_tgid(current); + queue.alter = alter; + queue.dupsop = dupsop; + + error = perform_atomic_semop(sma, &queue); + if (error == 0) { /* non-blocking successful path */ + DEFINE_WAKE_Q(wake_q); + + /* + * If the operation was successful, then do + * the required updates. + */ + if (alter) + do_smart_update(sma, sops, nsops, 1, &wake_q); + else + set_semotime(sma, sops); + + sem_unlock(sma, locknum); + rcu_read_unlock(); + wake_up_q(&wake_q); + + goto out; + } + if (error < 0) /* non-blocking error path */ + goto out_unlock; + + /* + * We need to sleep on this operation, so we put the current + * task into the pending queue and go to sleep. + */ + if (nsops == 1) { + struct sem *curr; + int idx = array_index_nospec(sops->sem_num, sma->sem_nsems); + curr = &sma->sems[idx]; + + if (alter) { + if (sma->complex_count) { + list_add_tail(&queue.list, + &sma->pending_alter); + } else { + + list_add_tail(&queue.list, + &curr->pending_alter); + } + } else { + list_add_tail(&queue.list, &curr->pending_const); + } + } else { + if (!sma->complex_count) + merge_queues(sma); + + if (alter) + list_add_tail(&queue.list, &sma->pending_alter); + else + list_add_tail(&queue.list, &sma->pending_const); + + sma->complex_count++; + } + + do { + /* memory ordering ensured by the lock in sem_lock() */ + WRITE_ONCE(queue.status, -EINTR); + queue.sleeper = current; + + /* memory ordering is ensured by the lock in sem_lock() */ + __set_current_state(TASK_INTERRUPTIBLE); + sem_unlock(sma, locknum); + rcu_read_unlock(); + + timed_out = !schedule_hrtimeout_range(exp, + current->timer_slack_ns, HRTIMER_MODE_ABS); + + /* + * fastpath: the semop has completed, either successfully or + * not, from the syscall pov, is quite irrelevant to us at this + * point; we're done. + * + * We _do_ care, nonetheless, about being awoken by a signal or + * spuriously. The queue.status is checked again in the + * slowpath (aka after taking sem_lock), such that we can detect + * scenarios where we were awakened externally, during the + * window between wake_q_add() and wake_up_q(). + */ + rcu_read_lock(); + error = READ_ONCE(queue.status); + if (error != -EINTR) { + /* see SEM_BARRIER_2 for purpose/pairing */ + smp_acquire__after_ctrl_dep(); + rcu_read_unlock(); + goto out; + } + + locknum = sem_lock(sma, sops, nsops); + + if (!ipc_valid_object(&sma->sem_perm)) + goto out_unlock; + + /* + * No necessity for any barrier: We are protect by sem_lock() + */ + error = READ_ONCE(queue.status); + + /* + * If queue.status != -EINTR we are woken up by another process. + * Leave without unlink_queue(), but with sem_unlock(). + */ + if (error != -EINTR) + goto out_unlock; + + /* + * If an interrupt occurred we have to clean up the queue. + */ + if (timed_out) + error = -EAGAIN; + } while (error == -EINTR && !signal_pending(current)); /* spurious */ + + unlink_queue(sma, &queue); + +out_unlock: + sem_unlock(sma, locknum); + rcu_read_unlock(); +out: + return error; +} + +static long do_semtimedop(int semid, struct sembuf __user *tsops, + unsigned nsops, const struct timespec64 *timeout) +{ + struct sembuf fast_sops[SEMOPM_FAST]; + struct sembuf *sops = fast_sops; + struct ipc_namespace *ns; + int ret; + + ns = current->nsproxy->ipc_ns; + if (nsops > ns->sc_semopm) + return -E2BIG; + if (nsops < 1) + return -EINVAL; + + if (nsops > SEMOPM_FAST) { + sops = kvmalloc_array(nsops, sizeof(*sops), GFP_KERNEL); + if (sops == NULL) + return -ENOMEM; + } + + if (copy_from_user(sops, tsops, nsops * sizeof(*tsops))) { + ret = -EFAULT; + goto out_free; + } + + ret = __do_semtimedop(semid, sops, nsops, timeout, ns); + +out_free: + if (sops != fast_sops) + kvfree(sops); + + return ret; +} + +long ksys_semtimedop(int semid, struct sembuf __user *tsops, + unsigned int nsops, const struct __kernel_timespec __user *timeout) +{ + if (timeout) { + struct timespec64 ts; + if (get_timespec64(&ts, timeout)) + return -EFAULT; + return do_semtimedop(semid, tsops, nsops, &ts); + } + return do_semtimedop(semid, tsops, nsops, NULL); +} + +SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops, + unsigned int, nsops, const struct __kernel_timespec __user *, timeout) +{ + return ksys_semtimedop(semid, tsops, nsops, timeout); +} + +#ifdef CONFIG_COMPAT_32BIT_TIME +long compat_ksys_semtimedop(int semid, struct sembuf __user *tsems, + unsigned int nsops, + const struct old_timespec32 __user *timeout) +{ + if (timeout) { + struct timespec64 ts; + if (get_old_timespec32(&ts, timeout)) + return -EFAULT; + return do_semtimedop(semid, tsems, nsops, &ts); + } + return do_semtimedop(semid, tsems, nsops, NULL); +} + +SYSCALL_DEFINE4(semtimedop_time32, int, semid, struct sembuf __user *, tsems, + unsigned int, nsops, + const struct old_timespec32 __user *, timeout) +{ + return compat_ksys_semtimedop(semid, tsems, nsops, timeout); +} +#endif + +SYSCALL_DEFINE3(semop, int, semid, struct sembuf __user *, tsops, + unsigned, nsops) +{ + return do_semtimedop(semid, tsops, nsops, NULL); +} + +/* If CLONE_SYSVSEM is set, establish sharing of SEM_UNDO state between + * parent and child tasks. + */ + +int copy_semundo(unsigned long clone_flags, struct task_struct *tsk) +{ + struct sem_undo_list *undo_list; + int error; + + if (clone_flags & CLONE_SYSVSEM) { + error = get_undo_list(&undo_list); + if (error) + return error; + refcount_inc(&undo_list->refcnt); + tsk->sysvsem.undo_list = undo_list; + } else + tsk->sysvsem.undo_list = NULL; + + return 0; +} + +/* + * add semadj values to semaphores, free undo structures. + * undo structures are not freed when semaphore arrays are destroyed + * so some of them may be out of date. + * IMPLEMENTATION NOTE: There is some confusion over whether the + * set of adjustments that needs to be done should be done in an atomic + * manner or not. That is, if we are attempting to decrement the semval + * should we queue up and wait until we can do so legally? + * The original implementation attempted to do this (queue and wait). + * The current implementation does not do so. The POSIX standard + * and SVID should be consulted to determine what behavior is mandated. + */ +void exit_sem(struct task_struct *tsk) +{ + struct sem_undo_list *ulp; + + ulp = tsk->sysvsem.undo_list; + if (!ulp) + return; + tsk->sysvsem.undo_list = NULL; + + if (!refcount_dec_and_test(&ulp->refcnt)) + return; + + for (;;) { + struct sem_array *sma; + struct sem_undo *un; + int semid, i; + DEFINE_WAKE_Q(wake_q); + + cond_resched(); + + rcu_read_lock(); + un = list_entry_rcu(ulp->list_proc.next, + struct sem_undo, list_proc); + if (&un->list_proc == &ulp->list_proc) { + /* + * We must wait for freeary() before freeing this ulp, + * in case we raced with last sem_undo. There is a small + * possibility where we exit while freeary() didn't + * finish unlocking sem_undo_list. + */ + spin_lock(&ulp->lock); + spin_unlock(&ulp->lock); + rcu_read_unlock(); + break; + } + spin_lock(&ulp->lock); + semid = un->semid; + spin_unlock(&ulp->lock); + + /* exit_sem raced with IPC_RMID, nothing to do */ + if (semid == -1) { + rcu_read_unlock(); + continue; + } + + sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, semid); + /* exit_sem raced with IPC_RMID, nothing to do */ + if (IS_ERR(sma)) { + rcu_read_unlock(); + continue; + } + + sem_lock(sma, NULL, -1); + /* exit_sem raced with IPC_RMID, nothing to do */ + if (!ipc_valid_object(&sma->sem_perm)) { + sem_unlock(sma, -1); + rcu_read_unlock(); + continue; + } + un = __lookup_undo(ulp, semid); + if (un == NULL) { + /* exit_sem raced with IPC_RMID+semget() that created + * exactly the same semid. Nothing to do. + */ + sem_unlock(sma, -1); + rcu_read_unlock(); + continue; + } + + /* remove un from the linked lists */ + ipc_assert_locked_object(&sma->sem_perm); + list_del(&un->list_id); + + spin_lock(&ulp->lock); + list_del_rcu(&un->list_proc); + spin_unlock(&ulp->lock); + + /* perform adjustments registered in un */ + for (i = 0; i < sma->sem_nsems; i++) { + struct sem *semaphore = &sma->sems[i]; + if (un->semadj[i]) { + semaphore->semval += un->semadj[i]; + /* + * Range checks of the new semaphore value, + * not defined by sus: + * - Some unices ignore the undo entirely + * (e.g. HP UX 11i 11.22, Tru64 V5.1) + * - some cap the value (e.g. FreeBSD caps + * at 0, but doesn't enforce SEMVMX) + * + * Linux caps the semaphore value, both at 0 + * and at SEMVMX. + * + * Manfred <manfred@colorfullife.com> + */ + if (semaphore->semval < 0) + semaphore->semval = 0; + if (semaphore->semval > SEMVMX) + semaphore->semval = SEMVMX; + ipc_update_pid(&semaphore->sempid, task_tgid(current)); + } + } + /* maybe some queued-up processes were waiting for this */ + do_smart_update(sma, NULL, 0, 1, &wake_q); + sem_unlock(sma, -1); + rcu_read_unlock(); + wake_up_q(&wake_q); + + kvfree_rcu(un, rcu); + } + kfree(ulp); +} + +#ifdef CONFIG_PROC_FS +static int sysvipc_sem_proc_show(struct seq_file *s, void *it) +{ + struct user_namespace *user_ns = seq_user_ns(s); + struct kern_ipc_perm *ipcp = it; + struct sem_array *sma = container_of(ipcp, struct sem_array, sem_perm); + time64_t sem_otime; + + /* + * The proc interface isn't aware of sem_lock(), it calls + * ipc_lock_object(), i.e. spin_lock(&sma->sem_perm.lock). + * (in sysvipc_find_ipc) + * In order to stay compatible with sem_lock(), we must + * enter / leave complex_mode. + */ + complexmode_enter(sma); + + sem_otime = get_semotime(sma); + + seq_printf(s, + "%10d %10d %4o %10u %5u %5u %5u %5u %10llu %10llu\n", + sma->sem_perm.key, + sma->sem_perm.id, + sma->sem_perm.mode, + sma->sem_nsems, + from_kuid_munged(user_ns, sma->sem_perm.uid), + from_kgid_munged(user_ns, sma->sem_perm.gid), + from_kuid_munged(user_ns, sma->sem_perm.cuid), + from_kgid_munged(user_ns, sma->sem_perm.cgid), + sem_otime, + sma->sem_ctime); + + complexmode_tryleave(sma); + + return 0; +} +#endif diff --git a/ipc/shm.c b/ipc/shm.c new file mode 100644 index 0000000000..576a543b7c --- /dev/null +++ b/ipc/shm.c @@ -0,0 +1,1883 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/ipc/shm.c + * Copyright (C) 1992, 1993 Krishna Balasubramanian + * Many improvements/fixes by Bruno Haible. + * Replaced `struct shm_desc' by `struct vm_area_struct', July 1994. + * Fixed the shm swap deallocation (shm_unuse()), August 1998 Andrea Arcangeli. + * + * /proc/sysvipc/shm support (c) 1999 Dragos Acostachioaie <dragos@iname.com> + * BIGMEM support, Andrea Arcangeli <andrea@suse.de> + * SMP thread shm, Jean-Luc Boyard <jean-luc.boyard@siemens.fr> + * HIGHMEM support, Ingo Molnar <mingo@redhat.com> + * Make shmmax, shmall, shmmni sysctl'able, Christoph Rohland <cr@sap.com> + * Shared /dev/zero support, Kanoj Sarcar <kanoj@sgi.com> + * Move the mm functionality over to mm/shmem.c, Christoph Rohland <cr@sap.com> + * + * support for audit of ipc object properties and permission changes + * Dustin Kirkland <dustin.kirkland@us.ibm.com> + * + * namespaces support + * OpenVZ, SWsoft Inc. + * Pavel Emelianov <xemul@openvz.org> + * + * Better ipc lock (kern_ipc_perm.lock) handling + * Davidlohr Bueso <davidlohr.bueso@hp.com>, June 2013. + */ + +#include <linux/slab.h> +#include <linux/mm.h> +#include <linux/hugetlb.h> +#include <linux/shm.h> +#include <linux/init.h> +#include <linux/file.h> +#include <linux/mman.h> +#include <linux/shmem_fs.h> +#include <linux/security.h> +#include <linux/syscalls.h> +#include <linux/audit.h> +#include <linux/capability.h> +#include <linux/ptrace.h> +#include <linux/seq_file.h> +#include <linux/rwsem.h> +#include <linux/nsproxy.h> +#include <linux/mount.h> +#include <linux/ipc_namespace.h> +#include <linux/rhashtable.h> + +#include <linux/uaccess.h> + +#include "util.h" + +struct shmid_kernel /* private to the kernel */ +{ + struct kern_ipc_perm shm_perm; + struct file *shm_file; + unsigned long shm_nattch; + unsigned long shm_segsz; + time64_t shm_atim; + time64_t shm_dtim; + time64_t shm_ctim; + struct pid *shm_cprid; + struct pid *shm_lprid; + struct ucounts *mlock_ucounts; + + /* + * The task created the shm object, for + * task_lock(shp->shm_creator) + */ + struct task_struct *shm_creator; + + /* + * List by creator. task_lock(->shm_creator) required for read/write. + * If list_empty(), then the creator is dead already. + */ + struct list_head shm_clist; + struct ipc_namespace *ns; +} __randomize_layout; + +/* shm_mode upper byte flags */ +#define SHM_DEST 01000 /* segment will be destroyed on last detach */ +#define SHM_LOCKED 02000 /* segment will not be swapped */ + +struct shm_file_data { + int id; + struct ipc_namespace *ns; + struct file *file; + const struct vm_operations_struct *vm_ops; +}; + +#define shm_file_data(file) (*((struct shm_file_data **)&(file)->private_data)) + +static const struct file_operations shm_file_operations; +static const struct vm_operations_struct shm_vm_ops; + +#define shm_ids(ns) ((ns)->ids[IPC_SHM_IDS]) + +#define shm_unlock(shp) \ + ipc_unlock(&(shp)->shm_perm) + +static int newseg(struct ipc_namespace *, struct ipc_params *); +static void shm_open(struct vm_area_struct *vma); +static void shm_close(struct vm_area_struct *vma); +static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp); +#ifdef CONFIG_PROC_FS +static int sysvipc_shm_proc_show(struct seq_file *s, void *it); +#endif + +void shm_init_ns(struct ipc_namespace *ns) +{ + ns->shm_ctlmax = SHMMAX; + ns->shm_ctlall = SHMALL; + ns->shm_ctlmni = SHMMNI; + ns->shm_rmid_forced = 0; + ns->shm_tot = 0; + ipc_init_ids(&shm_ids(ns)); +} + +/* + * Called with shm_ids.rwsem (writer) and the shp structure locked. + * Only shm_ids.rwsem remains locked on exit. + */ +static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) +{ + struct shmid_kernel *shp; + + shp = container_of(ipcp, struct shmid_kernel, shm_perm); + WARN_ON(ns != shp->ns); + + if (shp->shm_nattch) { + shp->shm_perm.mode |= SHM_DEST; + /* Do not find it any more */ + ipc_set_key_private(&shm_ids(ns), &shp->shm_perm); + shm_unlock(shp); + } else + shm_destroy(ns, shp); +} + +#ifdef CONFIG_IPC_NS +void shm_exit_ns(struct ipc_namespace *ns) +{ + free_ipcs(ns, &shm_ids(ns), do_shm_rmid); + idr_destroy(&ns->ids[IPC_SHM_IDS].ipcs_idr); + rhashtable_destroy(&ns->ids[IPC_SHM_IDS].key_ht); +} +#endif + +static int __init ipc_ns_init(void) +{ + shm_init_ns(&init_ipc_ns); + return 0; +} + +pure_initcall(ipc_ns_init); + +void __init shm_init(void) +{ + ipc_init_proc_interface("sysvipc/shm", +#if BITS_PER_LONG <= 32 + " key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime rss swap\n", +#else + " key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime rss swap\n", +#endif + IPC_SHM_IDS, sysvipc_shm_proc_show); +} + +static inline struct shmid_kernel *shm_obtain_object(struct ipc_namespace *ns, int id) +{ + struct kern_ipc_perm *ipcp = ipc_obtain_object_idr(&shm_ids(ns), id); + + if (IS_ERR(ipcp)) + return ERR_CAST(ipcp); + + return container_of(ipcp, struct shmid_kernel, shm_perm); +} + +static inline struct shmid_kernel *shm_obtain_object_check(struct ipc_namespace *ns, int id) +{ + struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&shm_ids(ns), id); + + if (IS_ERR(ipcp)) + return ERR_CAST(ipcp); + + return container_of(ipcp, struct shmid_kernel, shm_perm); +} + +/* + * shm_lock_(check_) routines are called in the paths where the rwsem + * is not necessarily held. + */ +static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id) +{ + struct kern_ipc_perm *ipcp; + + rcu_read_lock(); + ipcp = ipc_obtain_object_idr(&shm_ids(ns), id); + if (IS_ERR(ipcp)) + goto err; + + ipc_lock_object(ipcp); + /* + * ipc_rmid() may have already freed the ID while ipc_lock_object() + * was spinning: here verify that the structure is still valid. + * Upon races with RMID, return -EIDRM, thus indicating that + * the ID points to a removed identifier. + */ + if (ipc_valid_object(ipcp)) { + /* return a locked ipc object upon success */ + return container_of(ipcp, struct shmid_kernel, shm_perm); + } + + ipc_unlock_object(ipcp); + ipcp = ERR_PTR(-EIDRM); +err: + rcu_read_unlock(); + /* + * Callers of shm_lock() must validate the status of the returned ipc + * object pointer and error out as appropriate. + */ + return ERR_CAST(ipcp); +} + +static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp) +{ + rcu_read_lock(); + ipc_lock_object(&ipcp->shm_perm); +} + +static void shm_rcu_free(struct rcu_head *head) +{ + struct kern_ipc_perm *ptr = container_of(head, struct kern_ipc_perm, + rcu); + struct shmid_kernel *shp = container_of(ptr, struct shmid_kernel, + shm_perm); + security_shm_free(&shp->shm_perm); + kfree(shp); +} + +/* + * It has to be called with shp locked. + * It must be called before ipc_rmid() + */ +static inline void shm_clist_rm(struct shmid_kernel *shp) +{ + struct task_struct *creator; + + /* ensure that shm_creator does not disappear */ + rcu_read_lock(); + + /* + * A concurrent exit_shm may do a list_del_init() as well. + * Just do nothing if exit_shm already did the work + */ + if (!list_empty(&shp->shm_clist)) { + /* + * shp->shm_creator is guaranteed to be valid *only* + * if shp->shm_clist is not empty. + */ + creator = shp->shm_creator; + + task_lock(creator); + /* + * list_del_init() is a nop if the entry was already removed + * from the list. + */ + list_del_init(&shp->shm_clist); + task_unlock(creator); + } + rcu_read_unlock(); +} + +static inline void shm_rmid(struct shmid_kernel *s) +{ + shm_clist_rm(s); + ipc_rmid(&shm_ids(s->ns), &s->shm_perm); +} + + +static int __shm_open(struct shm_file_data *sfd) +{ + struct shmid_kernel *shp; + + shp = shm_lock(sfd->ns, sfd->id); + + if (IS_ERR(shp)) + return PTR_ERR(shp); + + if (shp->shm_file != sfd->file) { + /* ID was reused */ + shm_unlock(shp); + return -EINVAL; + } + + shp->shm_atim = ktime_get_real_seconds(); + ipc_update_pid(&shp->shm_lprid, task_tgid(current)); + shp->shm_nattch++; + shm_unlock(shp); + return 0; +} + +/* This is called by fork, once for every shm attach. */ +static void shm_open(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + int err; + + /* Always call underlying open if present */ + if (sfd->vm_ops->open) + sfd->vm_ops->open(vma); + + err = __shm_open(sfd); + /* + * We raced in the idr lookup or with shm_destroy(). + * Either way, the ID is busted. + */ + WARN_ON_ONCE(err); +} + +/* + * shm_destroy - free the struct shmid_kernel + * + * @ns: namespace + * @shp: struct to free + * + * It has to be called with shp and shm_ids.rwsem (writer) locked, + * but returns with shp unlocked and freed. + */ +static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) +{ + struct file *shm_file; + + shm_file = shp->shm_file; + shp->shm_file = NULL; + ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT; + shm_rmid(shp); + shm_unlock(shp); + if (!is_file_hugepages(shm_file)) + shmem_lock(shm_file, 0, shp->mlock_ucounts); + fput(shm_file); + ipc_update_pid(&shp->shm_cprid, NULL); + ipc_update_pid(&shp->shm_lprid, NULL); + ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); +} + +/* + * shm_may_destroy - identifies whether shm segment should be destroyed now + * + * Returns true if and only if there are no active users of the segment and + * one of the following is true: + * + * 1) shmctl(id, IPC_RMID, NULL) was called for this shp + * + * 2) sysctl kernel.shm_rmid_forced is set to 1. + */ +static bool shm_may_destroy(struct shmid_kernel *shp) +{ + return (shp->shm_nattch == 0) && + (shp->ns->shm_rmid_forced || + (shp->shm_perm.mode & SHM_DEST)); +} + +/* + * remove the attach descriptor vma. + * free memory for segment if it is marked destroyed. + * The descriptor has already been removed from the current->mm->mmap list + * and will later be kfree()d. + */ +static void __shm_close(struct shm_file_data *sfd) +{ + struct shmid_kernel *shp; + struct ipc_namespace *ns = sfd->ns; + + down_write(&shm_ids(ns).rwsem); + /* remove from the list of attaches of the shm segment */ + shp = shm_lock(ns, sfd->id); + + /* + * We raced in the idr lookup or with shm_destroy(). + * Either way, the ID is busted. + */ + if (WARN_ON_ONCE(IS_ERR(shp))) + goto done; /* no-op */ + + ipc_update_pid(&shp->shm_lprid, task_tgid(current)); + shp->shm_dtim = ktime_get_real_seconds(); + shp->shm_nattch--; + if (shm_may_destroy(shp)) + shm_destroy(ns, shp); + else + shm_unlock(shp); +done: + up_write(&shm_ids(ns).rwsem); +} + +static void shm_close(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + + /* Always call underlying close if present */ + if (sfd->vm_ops->close) + sfd->vm_ops->close(vma); + + __shm_close(sfd); +} + +/* Called with ns->shm_ids(ns).rwsem locked */ +static int shm_try_destroy_orphaned(int id, void *p, void *data) +{ + struct ipc_namespace *ns = data; + struct kern_ipc_perm *ipcp = p; + struct shmid_kernel *shp = container_of(ipcp, struct shmid_kernel, shm_perm); + + /* + * We want to destroy segments without users and with already + * exit'ed originating process. + * + * As shp->* are changed under rwsem, it's safe to skip shp locking. + */ + if (!list_empty(&shp->shm_clist)) + return 0; + + if (shm_may_destroy(shp)) { + shm_lock_by_ptr(shp); + shm_destroy(ns, shp); + } + return 0; +} + +void shm_destroy_orphaned(struct ipc_namespace *ns) +{ + down_write(&shm_ids(ns).rwsem); + if (shm_ids(ns).in_use) + idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_orphaned, ns); + up_write(&shm_ids(ns).rwsem); +} + +/* Locking assumes this will only be called with task == current */ +void exit_shm(struct task_struct *task) +{ + for (;;) { + struct shmid_kernel *shp; + struct ipc_namespace *ns; + + task_lock(task); + + if (list_empty(&task->sysvshm.shm_clist)) { + task_unlock(task); + break; + } + + shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel, + shm_clist); + + /* + * 1) Get pointer to the ipc namespace. It is worth to say + * that this pointer is guaranteed to be valid because + * shp lifetime is always shorter than namespace lifetime + * in which shp lives. + * We taken task_lock it means that shp won't be freed. + */ + ns = shp->ns; + + /* + * 2) If kernel.shm_rmid_forced is not set then only keep track of + * which shmids are orphaned, so that a later set of the sysctl + * can clean them up. + */ + if (!ns->shm_rmid_forced) + goto unlink_continue; + + /* + * 3) get a reference to the namespace. + * The refcount could be already 0. If it is 0, then + * the shm objects will be free by free_ipc_work(). + */ + ns = get_ipc_ns_not_zero(ns); + if (!ns) { +unlink_continue: + list_del_init(&shp->shm_clist); + task_unlock(task); + continue; + } + + /* + * 4) get a reference to shp. + * This cannot fail: shm_clist_rm() is called before + * ipc_rmid(), thus the refcount cannot be 0. + */ + WARN_ON(!ipc_rcu_getref(&shp->shm_perm)); + + /* + * 5) unlink the shm segment from the list of segments + * created by current. + * This must be done last. After unlinking, + * only the refcounts obtained above prevent IPC_RMID + * from destroying the segment or the namespace. + */ + list_del_init(&shp->shm_clist); + + task_unlock(task); + + /* + * 6) we have all references + * Thus lock & if needed destroy shp. + */ + down_write(&shm_ids(ns).rwsem); + shm_lock_by_ptr(shp); + /* + * rcu_read_lock was implicitly taken in shm_lock_by_ptr, it's + * safe to call ipc_rcu_putref here + */ + ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); + + if (ipc_valid_object(&shp->shm_perm)) { + if (shm_may_destroy(shp)) + shm_destroy(ns, shp); + else + shm_unlock(shp); + } else { + /* + * Someone else deleted the shp from namespace + * idr/kht while we have waited. + * Just unlock and continue. + */ + shm_unlock(shp); + } + + up_write(&shm_ids(ns).rwsem); + put_ipc_ns(ns); /* paired with get_ipc_ns_not_zero */ + } +} + +static vm_fault_t shm_fault(struct vm_fault *vmf) +{ + struct file *file = vmf->vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + + return sfd->vm_ops->fault(vmf); +} + +static int shm_may_split(struct vm_area_struct *vma, unsigned long addr) +{ + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + + if (sfd->vm_ops->may_split) + return sfd->vm_ops->may_split(vma, addr); + + return 0; +} + +static unsigned long shm_pagesize(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + + if (sfd->vm_ops->pagesize) + return sfd->vm_ops->pagesize(vma); + + return PAGE_SIZE; +} + +#ifdef CONFIG_NUMA +static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new) +{ + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + int err = 0; + + if (sfd->vm_ops->set_policy) + err = sfd->vm_ops->set_policy(vma, new); + return err; +} + +static struct mempolicy *shm_get_policy(struct vm_area_struct *vma, + unsigned long addr) +{ + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + struct mempolicy *pol = NULL; + + if (sfd->vm_ops->get_policy) + pol = sfd->vm_ops->get_policy(vma, addr); + else if (vma->vm_policy) + pol = vma->vm_policy; + + return pol; +} +#endif + +static int shm_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct shm_file_data *sfd = shm_file_data(file); + int ret; + + /* + * In case of remap_file_pages() emulation, the file can represent an + * IPC ID that was removed, and possibly even reused by another shm + * segment already. Propagate this case as an error to caller. + */ + ret = __shm_open(sfd); + if (ret) + return ret; + + ret = call_mmap(sfd->file, vma); + if (ret) { + __shm_close(sfd); + return ret; + } + sfd->vm_ops = vma->vm_ops; +#ifdef CONFIG_MMU + WARN_ON(!sfd->vm_ops->fault); +#endif + vma->vm_ops = &shm_vm_ops; + return 0; +} + +static int shm_release(struct inode *ino, struct file *file) +{ + struct shm_file_data *sfd = shm_file_data(file); + + put_ipc_ns(sfd->ns); + fput(sfd->file); + shm_file_data(file) = NULL; + kfree(sfd); + return 0; +} + +static int shm_fsync(struct file *file, loff_t start, loff_t end, int datasync) +{ + struct shm_file_data *sfd = shm_file_data(file); + + if (!sfd->file->f_op->fsync) + return -EINVAL; + return sfd->file->f_op->fsync(sfd->file, start, end, datasync); +} + +static long shm_fallocate(struct file *file, int mode, loff_t offset, + loff_t len) +{ + struct shm_file_data *sfd = shm_file_data(file); + + if (!sfd->file->f_op->fallocate) + return -EOPNOTSUPP; + return sfd->file->f_op->fallocate(file, mode, offset, len); +} + +static unsigned long shm_get_unmapped_area(struct file *file, + unsigned long addr, unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + struct shm_file_data *sfd = shm_file_data(file); + + return sfd->file->f_op->get_unmapped_area(sfd->file, addr, len, + pgoff, flags); +} + +static const struct file_operations shm_file_operations = { + .mmap = shm_mmap, + .fsync = shm_fsync, + .release = shm_release, + .get_unmapped_area = shm_get_unmapped_area, + .llseek = noop_llseek, + .fallocate = shm_fallocate, +}; + +/* + * shm_file_operations_huge is now identical to shm_file_operations, + * but we keep it distinct for the sake of is_file_shm_hugepages(). + */ +static const struct file_operations shm_file_operations_huge = { + .mmap = shm_mmap, + .fsync = shm_fsync, + .release = shm_release, + .get_unmapped_area = shm_get_unmapped_area, + .llseek = noop_llseek, + .fallocate = shm_fallocate, +}; + +bool is_file_shm_hugepages(struct file *file) +{ + return file->f_op == &shm_file_operations_huge; +} + +static const struct vm_operations_struct shm_vm_ops = { + .open = shm_open, /* callback for a new vm-area open */ + .close = shm_close, /* callback for when the vm-area is released */ + .fault = shm_fault, + .may_split = shm_may_split, + .pagesize = shm_pagesize, +#if defined(CONFIG_NUMA) + .set_policy = shm_set_policy, + .get_policy = shm_get_policy, +#endif +}; + +/** + * newseg - Create a new shared memory segment + * @ns: namespace + * @params: ptr to the structure that contains key, size and shmflg + * + * Called with shm_ids.rwsem held as a writer. + */ +static int newseg(struct ipc_namespace *ns, struct ipc_params *params) +{ + key_t key = params->key; + int shmflg = params->flg; + size_t size = params->u.size; + int error; + struct shmid_kernel *shp; + size_t numpages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; + struct file *file; + char name[13]; + vm_flags_t acctflag = 0; + + if (size < SHMMIN || size > ns->shm_ctlmax) + return -EINVAL; + + if (numpages << PAGE_SHIFT < size) + return -ENOSPC; + + if (ns->shm_tot + numpages < ns->shm_tot || + ns->shm_tot + numpages > ns->shm_ctlall) + return -ENOSPC; + + shp = kmalloc(sizeof(*shp), GFP_KERNEL_ACCOUNT); + if (unlikely(!shp)) + return -ENOMEM; + + shp->shm_perm.key = key; + shp->shm_perm.mode = (shmflg & S_IRWXUGO); + shp->mlock_ucounts = NULL; + + shp->shm_perm.security = NULL; + error = security_shm_alloc(&shp->shm_perm); + if (error) { + kfree(shp); + return error; + } + + sprintf(name, "SYSV%08x", key); + if (shmflg & SHM_HUGETLB) { + struct hstate *hs; + size_t hugesize; + + hs = hstate_sizelog((shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK); + if (!hs) { + error = -EINVAL; + goto no_file; + } + hugesize = ALIGN(size, huge_page_size(hs)); + + /* hugetlb_file_setup applies strict accounting */ + if (shmflg & SHM_NORESERVE) + acctflag = VM_NORESERVE; + file = hugetlb_file_setup(name, hugesize, acctflag, + HUGETLB_SHMFS_INODE, (shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK); + } else { + /* + * Do not allow no accounting for OVERCOMMIT_NEVER, even + * if it's asked for. + */ + if ((shmflg & SHM_NORESERVE) && + sysctl_overcommit_memory != OVERCOMMIT_NEVER) + acctflag = VM_NORESERVE; + file = shmem_kernel_file_setup(name, size, acctflag); + } + error = PTR_ERR(file); + if (IS_ERR(file)) + goto no_file; + + shp->shm_cprid = get_pid(task_tgid(current)); + shp->shm_lprid = NULL; + shp->shm_atim = shp->shm_dtim = 0; + shp->shm_ctim = ktime_get_real_seconds(); + shp->shm_segsz = size; + shp->shm_nattch = 0; + shp->shm_file = file; + shp->shm_creator = current; + + /* ipc_addid() locks shp upon success. */ + error = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni); + if (error < 0) + goto no_id; + + shp->ns = ns; + + task_lock(current); + list_add(&shp->shm_clist, ¤t->sysvshm.shm_clist); + task_unlock(current); + + /* + * shmid gets reported as "inode#" in /proc/pid/maps. + * proc-ps tools use this. Changing this will break them. + */ + file_inode(file)->i_ino = shp->shm_perm.id; + + ns->shm_tot += numpages; + error = shp->shm_perm.id; + + ipc_unlock_object(&shp->shm_perm); + rcu_read_unlock(); + return error; + +no_id: + ipc_update_pid(&shp->shm_cprid, NULL); + ipc_update_pid(&shp->shm_lprid, NULL); + fput(file); + ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); + return error; +no_file: + call_rcu(&shp->shm_perm.rcu, shm_rcu_free); + return error; +} + +/* + * Called with shm_ids.rwsem and ipcp locked. + */ +static int shm_more_checks(struct kern_ipc_perm *ipcp, struct ipc_params *params) +{ + struct shmid_kernel *shp; + + shp = container_of(ipcp, struct shmid_kernel, shm_perm); + if (shp->shm_segsz < params->u.size) + return -EINVAL; + + return 0; +} + +long ksys_shmget(key_t key, size_t size, int shmflg) +{ + struct ipc_namespace *ns; + static const struct ipc_ops shm_ops = { + .getnew = newseg, + .associate = security_shm_associate, + .more_checks = shm_more_checks, + }; + struct ipc_params shm_params; + + ns = current->nsproxy->ipc_ns; + + shm_params.key = key; + shm_params.flg = shmflg; + shm_params.u.size = size; + + return ipcget(ns, &shm_ids(ns), &shm_ops, &shm_params); +} + +SYSCALL_DEFINE3(shmget, key_t, key, size_t, size, int, shmflg) +{ + return ksys_shmget(key, size, shmflg); +} + +static inline unsigned long copy_shmid_to_user(void __user *buf, struct shmid64_ds *in, int version) +{ + switch (version) { + case IPC_64: + return copy_to_user(buf, in, sizeof(*in)); + case IPC_OLD: + { + struct shmid_ds out; + + memset(&out, 0, sizeof(out)); + ipc64_perm_to_ipc_perm(&in->shm_perm, &out.shm_perm); + out.shm_segsz = in->shm_segsz; + out.shm_atime = in->shm_atime; + out.shm_dtime = in->shm_dtime; + out.shm_ctime = in->shm_ctime; + out.shm_cpid = in->shm_cpid; + out.shm_lpid = in->shm_lpid; + out.shm_nattch = in->shm_nattch; + + return copy_to_user(buf, &out, sizeof(out)); + } + default: + return -EINVAL; + } +} + +static inline unsigned long +copy_shmid_from_user(struct shmid64_ds *out, void __user *buf, int version) +{ + switch (version) { + case IPC_64: + if (copy_from_user(out, buf, sizeof(*out))) + return -EFAULT; + return 0; + case IPC_OLD: + { + struct shmid_ds tbuf_old; + + if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old))) + return -EFAULT; + + out->shm_perm.uid = tbuf_old.shm_perm.uid; + out->shm_perm.gid = tbuf_old.shm_perm.gid; + out->shm_perm.mode = tbuf_old.shm_perm.mode; + + return 0; + } + default: + return -EINVAL; + } +} + +static inline unsigned long copy_shminfo_to_user(void __user *buf, struct shminfo64 *in, int version) +{ + switch (version) { + case IPC_64: + return copy_to_user(buf, in, sizeof(*in)); + case IPC_OLD: + { + struct shminfo out; + + if (in->shmmax > INT_MAX) + out.shmmax = INT_MAX; + else + out.shmmax = (int)in->shmmax; + + out.shmmin = in->shmmin; + out.shmmni = in->shmmni; + out.shmseg = in->shmseg; + out.shmall = in->shmall; + + return copy_to_user(buf, &out, sizeof(out)); + } + default: + return -EINVAL; + } +} + +/* + * Calculate and add used RSS and swap pages of a shm. + * Called with shm_ids.rwsem held as a reader + */ +static void shm_add_rss_swap(struct shmid_kernel *shp, + unsigned long *rss_add, unsigned long *swp_add) +{ + struct inode *inode; + + inode = file_inode(shp->shm_file); + + if (is_file_hugepages(shp->shm_file)) { + struct address_space *mapping = inode->i_mapping; + struct hstate *h = hstate_file(shp->shm_file); + *rss_add += pages_per_huge_page(h) * mapping->nrpages; + } else { +#ifdef CONFIG_SHMEM + struct shmem_inode_info *info = SHMEM_I(inode); + + spin_lock_irq(&info->lock); + *rss_add += inode->i_mapping->nrpages; + *swp_add += info->swapped; + spin_unlock_irq(&info->lock); +#else + *rss_add += inode->i_mapping->nrpages; +#endif + } +} + +/* + * Called with shm_ids.rwsem held as a reader + */ +static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss, + unsigned long *swp) +{ + int next_id; + int total, in_use; + + *rss = 0; + *swp = 0; + + in_use = shm_ids(ns).in_use; + + for (total = 0, next_id = 0; total < in_use; next_id++) { + struct kern_ipc_perm *ipc; + struct shmid_kernel *shp; + + ipc = idr_find(&shm_ids(ns).ipcs_idr, next_id); + if (ipc == NULL) + continue; + shp = container_of(ipc, struct shmid_kernel, shm_perm); + + shm_add_rss_swap(shp, rss, swp); + + total++; + } +} + +/* + * This function handles some shmctl commands which require the rwsem + * to be held in write mode. + * NOTE: no locks must be held, the rwsem is taken inside this function. + */ +static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd, + struct shmid64_ds *shmid64) +{ + struct kern_ipc_perm *ipcp; + struct shmid_kernel *shp; + int err; + + down_write(&shm_ids(ns).rwsem); + rcu_read_lock(); + + ipcp = ipcctl_obtain_check(ns, &shm_ids(ns), shmid, cmd, + &shmid64->shm_perm, 0); + if (IS_ERR(ipcp)) { + err = PTR_ERR(ipcp); + goto out_unlock1; + } + + shp = container_of(ipcp, struct shmid_kernel, shm_perm); + + err = security_shm_shmctl(&shp->shm_perm, cmd); + if (err) + goto out_unlock1; + + switch (cmd) { + case IPC_RMID: + ipc_lock_object(&shp->shm_perm); + /* do_shm_rmid unlocks the ipc object and rcu */ + do_shm_rmid(ns, ipcp); + goto out_up; + case IPC_SET: + ipc_lock_object(&shp->shm_perm); + err = ipc_update_perm(&shmid64->shm_perm, ipcp); + if (err) + goto out_unlock0; + shp->shm_ctim = ktime_get_real_seconds(); + break; + default: + err = -EINVAL; + goto out_unlock1; + } + +out_unlock0: + ipc_unlock_object(&shp->shm_perm); +out_unlock1: + rcu_read_unlock(); +out_up: + up_write(&shm_ids(ns).rwsem); + return err; +} + +static int shmctl_ipc_info(struct ipc_namespace *ns, + struct shminfo64 *shminfo) +{ + int err = security_shm_shmctl(NULL, IPC_INFO); + if (!err) { + memset(shminfo, 0, sizeof(*shminfo)); + shminfo->shmmni = shminfo->shmseg = ns->shm_ctlmni; + shminfo->shmmax = ns->shm_ctlmax; + shminfo->shmall = ns->shm_ctlall; + shminfo->shmmin = SHMMIN; + down_read(&shm_ids(ns).rwsem); + err = ipc_get_maxidx(&shm_ids(ns)); + up_read(&shm_ids(ns).rwsem); + if (err < 0) + err = 0; + } + return err; +} + +static int shmctl_shm_info(struct ipc_namespace *ns, + struct shm_info *shm_info) +{ + int err = security_shm_shmctl(NULL, SHM_INFO); + if (!err) { + memset(shm_info, 0, sizeof(*shm_info)); + down_read(&shm_ids(ns).rwsem); + shm_info->used_ids = shm_ids(ns).in_use; + shm_get_stat(ns, &shm_info->shm_rss, &shm_info->shm_swp); + shm_info->shm_tot = ns->shm_tot; + shm_info->swap_attempts = 0; + shm_info->swap_successes = 0; + err = ipc_get_maxidx(&shm_ids(ns)); + up_read(&shm_ids(ns).rwsem); + if (err < 0) + err = 0; + } + return err; +} + +static int shmctl_stat(struct ipc_namespace *ns, int shmid, + int cmd, struct shmid64_ds *tbuf) +{ + struct shmid_kernel *shp; + int err; + + memset(tbuf, 0, sizeof(*tbuf)); + + rcu_read_lock(); + if (cmd == SHM_STAT || cmd == SHM_STAT_ANY) { + shp = shm_obtain_object(ns, shmid); + if (IS_ERR(shp)) { + err = PTR_ERR(shp); + goto out_unlock; + } + } else { /* IPC_STAT */ + shp = shm_obtain_object_check(ns, shmid); + if (IS_ERR(shp)) { + err = PTR_ERR(shp); + goto out_unlock; + } + } + + /* + * Semantically SHM_STAT_ANY ought to be identical to + * that functionality provided by the /proc/sysvipc/ + * interface. As such, only audit these calls and + * do not do traditional S_IRUGO permission checks on + * the ipc object. + */ + if (cmd == SHM_STAT_ANY) + audit_ipc_obj(&shp->shm_perm); + else { + err = -EACCES; + if (ipcperms(ns, &shp->shm_perm, S_IRUGO)) + goto out_unlock; + } + + err = security_shm_shmctl(&shp->shm_perm, cmd); + if (err) + goto out_unlock; + + ipc_lock_object(&shp->shm_perm); + + if (!ipc_valid_object(&shp->shm_perm)) { + ipc_unlock_object(&shp->shm_perm); + err = -EIDRM; + goto out_unlock; + } + + kernel_to_ipc64_perm(&shp->shm_perm, &tbuf->shm_perm); + tbuf->shm_segsz = shp->shm_segsz; + tbuf->shm_atime = shp->shm_atim; + tbuf->shm_dtime = shp->shm_dtim; + tbuf->shm_ctime = shp->shm_ctim; +#ifndef CONFIG_64BIT + tbuf->shm_atime_high = shp->shm_atim >> 32; + tbuf->shm_dtime_high = shp->shm_dtim >> 32; + tbuf->shm_ctime_high = shp->shm_ctim >> 32; +#endif + tbuf->shm_cpid = pid_vnr(shp->shm_cprid); + tbuf->shm_lpid = pid_vnr(shp->shm_lprid); + tbuf->shm_nattch = shp->shm_nattch; + + if (cmd == IPC_STAT) { + /* + * As defined in SUS: + * Return 0 on success + */ + err = 0; + } else { + /* + * SHM_STAT and SHM_STAT_ANY (both Linux specific) + * Return the full id, including the sequence number + */ + err = shp->shm_perm.id; + } + + ipc_unlock_object(&shp->shm_perm); +out_unlock: + rcu_read_unlock(); + return err; +} + +static int shmctl_do_lock(struct ipc_namespace *ns, int shmid, int cmd) +{ + struct shmid_kernel *shp; + struct file *shm_file; + int err; + + rcu_read_lock(); + shp = shm_obtain_object_check(ns, shmid); + if (IS_ERR(shp)) { + err = PTR_ERR(shp); + goto out_unlock1; + } + + audit_ipc_obj(&(shp->shm_perm)); + err = security_shm_shmctl(&shp->shm_perm, cmd); + if (err) + goto out_unlock1; + + ipc_lock_object(&shp->shm_perm); + + /* check if shm_destroy() is tearing down shp */ + if (!ipc_valid_object(&shp->shm_perm)) { + err = -EIDRM; + goto out_unlock0; + } + + if (!ns_capable(ns->user_ns, CAP_IPC_LOCK)) { + kuid_t euid = current_euid(); + + if (!uid_eq(euid, shp->shm_perm.uid) && + !uid_eq(euid, shp->shm_perm.cuid)) { + err = -EPERM; + goto out_unlock0; + } + if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK)) { + err = -EPERM; + goto out_unlock0; + } + } + + shm_file = shp->shm_file; + if (is_file_hugepages(shm_file)) + goto out_unlock0; + + if (cmd == SHM_LOCK) { + struct ucounts *ucounts = current_ucounts(); + + err = shmem_lock(shm_file, 1, ucounts); + if (!err && !(shp->shm_perm.mode & SHM_LOCKED)) { + shp->shm_perm.mode |= SHM_LOCKED; + shp->mlock_ucounts = ucounts; + } + goto out_unlock0; + } + + /* SHM_UNLOCK */ + if (!(shp->shm_perm.mode & SHM_LOCKED)) + goto out_unlock0; + shmem_lock(shm_file, 0, shp->mlock_ucounts); + shp->shm_perm.mode &= ~SHM_LOCKED; + shp->mlock_ucounts = NULL; + get_file(shm_file); + ipc_unlock_object(&shp->shm_perm); + rcu_read_unlock(); + shmem_unlock_mapping(shm_file->f_mapping); + + fput(shm_file); + return err; + +out_unlock0: + ipc_unlock_object(&shp->shm_perm); +out_unlock1: + rcu_read_unlock(); + return err; +} + +static long ksys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf, int version) +{ + int err; + struct ipc_namespace *ns; + struct shmid64_ds sem64; + + if (cmd < 0 || shmid < 0) + return -EINVAL; + + ns = current->nsproxy->ipc_ns; + + switch (cmd) { + case IPC_INFO: { + struct shminfo64 shminfo; + err = shmctl_ipc_info(ns, &shminfo); + if (err < 0) + return err; + if (copy_shminfo_to_user(buf, &shminfo, version)) + err = -EFAULT; + return err; + } + case SHM_INFO: { + struct shm_info shm_info; + err = shmctl_shm_info(ns, &shm_info); + if (err < 0) + return err; + if (copy_to_user(buf, &shm_info, sizeof(shm_info))) + err = -EFAULT; + return err; + } + case SHM_STAT: + case SHM_STAT_ANY: + case IPC_STAT: { + err = shmctl_stat(ns, shmid, cmd, &sem64); + if (err < 0) + return err; + if (copy_shmid_to_user(buf, &sem64, version)) + err = -EFAULT; + return err; + } + case IPC_SET: + if (copy_shmid_from_user(&sem64, buf, version)) + return -EFAULT; + fallthrough; + case IPC_RMID: + return shmctl_down(ns, shmid, cmd, &sem64); + case SHM_LOCK: + case SHM_UNLOCK: + return shmctl_do_lock(ns, shmid, cmd); + default: + return -EINVAL; + } +} + +SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) +{ + return ksys_shmctl(shmid, cmd, buf, IPC_64); +} + +#ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION +long ksys_old_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) +{ + int version = ipc_parse_version(&cmd); + + return ksys_shmctl(shmid, cmd, buf, version); +} + +SYSCALL_DEFINE3(old_shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) +{ + return ksys_old_shmctl(shmid, cmd, buf); +} +#endif + +#ifdef CONFIG_COMPAT + +struct compat_shmid_ds { + struct compat_ipc_perm shm_perm; + int shm_segsz; + old_time32_t shm_atime; + old_time32_t shm_dtime; + old_time32_t shm_ctime; + compat_ipc_pid_t shm_cpid; + compat_ipc_pid_t shm_lpid; + unsigned short shm_nattch; + unsigned short shm_unused; + compat_uptr_t shm_unused2; + compat_uptr_t shm_unused3; +}; + +struct compat_shminfo64 { + compat_ulong_t shmmax; + compat_ulong_t shmmin; + compat_ulong_t shmmni; + compat_ulong_t shmseg; + compat_ulong_t shmall; + compat_ulong_t __unused1; + compat_ulong_t __unused2; + compat_ulong_t __unused3; + compat_ulong_t __unused4; +}; + +struct compat_shm_info { + compat_int_t used_ids; + compat_ulong_t shm_tot, shm_rss, shm_swp; + compat_ulong_t swap_attempts, swap_successes; +}; + +static int copy_compat_shminfo_to_user(void __user *buf, struct shminfo64 *in, + int version) +{ + if (in->shmmax > INT_MAX) + in->shmmax = INT_MAX; + if (version == IPC_64) { + struct compat_shminfo64 info; + memset(&info, 0, sizeof(info)); + info.shmmax = in->shmmax; + info.shmmin = in->shmmin; + info.shmmni = in->shmmni; + info.shmseg = in->shmseg; + info.shmall = in->shmall; + return copy_to_user(buf, &info, sizeof(info)); + } else { + struct shminfo info; + memset(&info, 0, sizeof(info)); + info.shmmax = in->shmmax; + info.shmmin = in->shmmin; + info.shmmni = in->shmmni; + info.shmseg = in->shmseg; + info.shmall = in->shmall; + return copy_to_user(buf, &info, sizeof(info)); + } +} + +static int put_compat_shm_info(struct shm_info *ip, + struct compat_shm_info __user *uip) +{ + struct compat_shm_info info; + + memset(&info, 0, sizeof(info)); + info.used_ids = ip->used_ids; + info.shm_tot = ip->shm_tot; + info.shm_rss = ip->shm_rss; + info.shm_swp = ip->shm_swp; + info.swap_attempts = ip->swap_attempts; + info.swap_successes = ip->swap_successes; + return copy_to_user(uip, &info, sizeof(info)); +} + +static int copy_compat_shmid_to_user(void __user *buf, struct shmid64_ds *in, + int version) +{ + if (version == IPC_64) { + struct compat_shmid64_ds v; + memset(&v, 0, sizeof(v)); + to_compat_ipc64_perm(&v.shm_perm, &in->shm_perm); + v.shm_atime = lower_32_bits(in->shm_atime); + v.shm_atime_high = upper_32_bits(in->shm_atime); + v.shm_dtime = lower_32_bits(in->shm_dtime); + v.shm_dtime_high = upper_32_bits(in->shm_dtime); + v.shm_ctime = lower_32_bits(in->shm_ctime); + v.shm_ctime_high = upper_32_bits(in->shm_ctime); + v.shm_segsz = in->shm_segsz; + v.shm_nattch = in->shm_nattch; + v.shm_cpid = in->shm_cpid; + v.shm_lpid = in->shm_lpid; + return copy_to_user(buf, &v, sizeof(v)); + } else { + struct compat_shmid_ds v; + memset(&v, 0, sizeof(v)); + to_compat_ipc_perm(&v.shm_perm, &in->shm_perm); + v.shm_perm.key = in->shm_perm.key; + v.shm_atime = in->shm_atime; + v.shm_dtime = in->shm_dtime; + v.shm_ctime = in->shm_ctime; + v.shm_segsz = in->shm_segsz; + v.shm_nattch = in->shm_nattch; + v.shm_cpid = in->shm_cpid; + v.shm_lpid = in->shm_lpid; + return copy_to_user(buf, &v, sizeof(v)); + } +} + +static int copy_compat_shmid_from_user(struct shmid64_ds *out, void __user *buf, + int version) +{ + memset(out, 0, sizeof(*out)); + if (version == IPC_64) { + struct compat_shmid64_ds __user *p = buf; + return get_compat_ipc64_perm(&out->shm_perm, &p->shm_perm); + } else { + struct compat_shmid_ds __user *p = buf; + return get_compat_ipc_perm(&out->shm_perm, &p->shm_perm); + } +} + +static long compat_ksys_shmctl(int shmid, int cmd, void __user *uptr, int version) +{ + struct ipc_namespace *ns; + struct shmid64_ds sem64; + int err; + + ns = current->nsproxy->ipc_ns; + + if (cmd < 0 || shmid < 0) + return -EINVAL; + + switch (cmd) { + case IPC_INFO: { + struct shminfo64 shminfo; + err = shmctl_ipc_info(ns, &shminfo); + if (err < 0) + return err; + if (copy_compat_shminfo_to_user(uptr, &shminfo, version)) + err = -EFAULT; + return err; + } + case SHM_INFO: { + struct shm_info shm_info; + err = shmctl_shm_info(ns, &shm_info); + if (err < 0) + return err; + if (put_compat_shm_info(&shm_info, uptr)) + err = -EFAULT; + return err; + } + case IPC_STAT: + case SHM_STAT_ANY: + case SHM_STAT: + err = shmctl_stat(ns, shmid, cmd, &sem64); + if (err < 0) + return err; + if (copy_compat_shmid_to_user(uptr, &sem64, version)) + err = -EFAULT; + return err; + + case IPC_SET: + if (copy_compat_shmid_from_user(&sem64, uptr, version)) + return -EFAULT; + fallthrough; + case IPC_RMID: + return shmctl_down(ns, shmid, cmd, &sem64); + case SHM_LOCK: + case SHM_UNLOCK: + return shmctl_do_lock(ns, shmid, cmd); + default: + return -EINVAL; + } + return err; +} + +COMPAT_SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, void __user *, uptr) +{ + return compat_ksys_shmctl(shmid, cmd, uptr, IPC_64); +} + +#ifdef CONFIG_ARCH_WANT_COMPAT_IPC_PARSE_VERSION +long compat_ksys_old_shmctl(int shmid, int cmd, void __user *uptr) +{ + int version = compat_ipc_parse_version(&cmd); + + return compat_ksys_shmctl(shmid, cmd, uptr, version); +} + +COMPAT_SYSCALL_DEFINE3(old_shmctl, int, shmid, int, cmd, void __user *, uptr) +{ + return compat_ksys_old_shmctl(shmid, cmd, uptr); +} +#endif +#endif + +/* + * Fix shmaddr, allocate descriptor, map shm, add attach descriptor to lists. + * + * NOTE! Despite the name, this is NOT a direct system call entrypoint. The + * "raddr" thing points to kernel space, and there has to be a wrapper around + * this. + */ +long do_shmat(int shmid, char __user *shmaddr, int shmflg, + ulong *raddr, unsigned long shmlba) +{ + struct shmid_kernel *shp; + unsigned long addr = (unsigned long)shmaddr; + unsigned long size; + struct file *file, *base; + int err; + unsigned long flags = MAP_SHARED; + unsigned long prot; + int acc_mode; + struct ipc_namespace *ns; + struct shm_file_data *sfd; + int f_flags; + unsigned long populate = 0; + + err = -EINVAL; + if (shmid < 0) + goto out; + + if (addr) { + if (addr & (shmlba - 1)) { + if (shmflg & SHM_RND) { + addr &= ~(shmlba - 1); /* round down */ + + /* + * Ensure that the round-down is non-nil + * when remapping. This can happen for + * cases when addr < shmlba. + */ + if (!addr && (shmflg & SHM_REMAP)) + goto out; + } else +#ifndef __ARCH_FORCE_SHMLBA + if (addr & ~PAGE_MASK) +#endif + goto out; + } + + flags |= MAP_FIXED; + } else if ((shmflg & SHM_REMAP)) + goto out; + + if (shmflg & SHM_RDONLY) { + prot = PROT_READ; + acc_mode = S_IRUGO; + f_flags = O_RDONLY; + } else { + prot = PROT_READ | PROT_WRITE; + acc_mode = S_IRUGO | S_IWUGO; + f_flags = O_RDWR; + } + if (shmflg & SHM_EXEC) { + prot |= PROT_EXEC; + acc_mode |= S_IXUGO; + } + + /* + * We cannot rely on the fs check since SYSV IPC does have an + * additional creator id... + */ + ns = current->nsproxy->ipc_ns; + rcu_read_lock(); + shp = shm_obtain_object_check(ns, shmid); + if (IS_ERR(shp)) { + err = PTR_ERR(shp); + goto out_unlock; + } + + err = -EACCES; + if (ipcperms(ns, &shp->shm_perm, acc_mode)) + goto out_unlock; + + err = security_shm_shmat(&shp->shm_perm, shmaddr, shmflg); + if (err) + goto out_unlock; + + ipc_lock_object(&shp->shm_perm); + + /* check if shm_destroy() is tearing down shp */ + if (!ipc_valid_object(&shp->shm_perm)) { + ipc_unlock_object(&shp->shm_perm); + err = -EIDRM; + goto out_unlock; + } + + /* + * We need to take a reference to the real shm file to prevent the + * pointer from becoming stale in cases where the lifetime of the outer + * file extends beyond that of the shm segment. It's not usually + * possible, but it can happen during remap_file_pages() emulation as + * that unmaps the memory, then does ->mmap() via file reference only. + * We'll deny the ->mmap() if the shm segment was since removed, but to + * detect shm ID reuse we need to compare the file pointers. + */ + base = get_file(shp->shm_file); + shp->shm_nattch++; + size = i_size_read(file_inode(base)); + ipc_unlock_object(&shp->shm_perm); + rcu_read_unlock(); + + err = -ENOMEM; + sfd = kzalloc(sizeof(*sfd), GFP_KERNEL); + if (!sfd) { + fput(base); + goto out_nattch; + } + + file = alloc_file_clone(base, f_flags, + is_file_hugepages(base) ? + &shm_file_operations_huge : + &shm_file_operations); + err = PTR_ERR(file); + if (IS_ERR(file)) { + kfree(sfd); + fput(base); + goto out_nattch; + } + + sfd->id = shp->shm_perm.id; + sfd->ns = get_ipc_ns(ns); + sfd->file = base; + sfd->vm_ops = NULL; + file->private_data = sfd; + + err = security_mmap_file(file, prot, flags); + if (err) + goto out_fput; + + if (mmap_write_lock_killable(current->mm)) { + err = -EINTR; + goto out_fput; + } + + if (addr && !(shmflg & SHM_REMAP)) { + err = -EINVAL; + if (addr + size < addr) + goto invalid; + + if (find_vma_intersection(current->mm, addr, addr + size)) + goto invalid; + } + + addr = do_mmap(file, addr, size, prot, flags, 0, 0, &populate, NULL); + *raddr = addr; + err = 0; + if (IS_ERR_VALUE(addr)) + err = (long)addr; +invalid: + mmap_write_unlock(current->mm); + if (populate) + mm_populate(addr, populate); + +out_fput: + fput(file); + +out_nattch: + down_write(&shm_ids(ns).rwsem); + shp = shm_lock(ns, shmid); + shp->shm_nattch--; + + if (shm_may_destroy(shp)) + shm_destroy(ns, shp); + else + shm_unlock(shp); + up_write(&shm_ids(ns).rwsem); + return err; + +out_unlock: + rcu_read_unlock(); +out: + return err; +} + +SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg) +{ + unsigned long ret; + long err; + + err = do_shmat(shmid, shmaddr, shmflg, &ret, SHMLBA); + if (err) + return err; + force_successful_syscall_return(); + return (long)ret; +} + +#ifdef CONFIG_COMPAT + +#ifndef COMPAT_SHMLBA +#define COMPAT_SHMLBA SHMLBA +#endif + +COMPAT_SYSCALL_DEFINE3(shmat, int, shmid, compat_uptr_t, shmaddr, int, shmflg) +{ + unsigned long ret; + long err; + + err = do_shmat(shmid, compat_ptr(shmaddr), shmflg, &ret, COMPAT_SHMLBA); + if (err) + return err; + force_successful_syscall_return(); + return (long)ret; +} +#endif + +/* + * detach and kill segment if marked destroyed. + * The work is done in shm_close. + */ +long ksys_shmdt(char __user *shmaddr) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long addr = (unsigned long)shmaddr; + int retval = -EINVAL; +#ifdef CONFIG_MMU + loff_t size = 0; + struct file *file; + VMA_ITERATOR(vmi, mm, addr); +#endif + + if (addr & ~PAGE_MASK) + return retval; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + /* + * This function tries to be smart and unmap shm segments that + * were modified by partial mlock or munmap calls: + * - It first determines the size of the shm segment that should be + * unmapped: It searches for a vma that is backed by shm and that + * started at address shmaddr. It records it's size and then unmaps + * it. + * - Then it unmaps all shm vmas that started at shmaddr and that + * are within the initially determined size and that are from the + * same shm segment from which we determined the size. + * Errors from do_munmap are ignored: the function only fails if + * it's called with invalid parameters or if it's called to unmap + * a part of a vma. Both calls in this function are for full vmas, + * the parameters are directly copied from the vma itself and always + * valid - therefore do_munmap cannot fail. (famous last words?) + */ + /* + * If it had been mremap()'d, the starting address would not + * match the usual checks anyway. So assume all vma's are + * above the starting address given. + */ + +#ifdef CONFIG_MMU + for_each_vma(vmi, vma) { + /* + * Check if the starting address would match, i.e. it's + * a fragment created by mprotect() and/or munmap(), or it + * otherwise it starts at this address with no hassles. + */ + if ((vma->vm_ops == &shm_vm_ops) && + (vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) { + + /* + * Record the file of the shm segment being + * unmapped. With mremap(), someone could place + * page from another segment but with equal offsets + * in the range we are unmapping. + */ + file = vma->vm_file; + size = i_size_read(file_inode(vma->vm_file)); + do_vma_munmap(&vmi, vma, vma->vm_start, vma->vm_end, + NULL, false); + /* + * We discovered the size of the shm segment, so + * break out of here and fall through to the next + * loop that uses the size information to stop + * searching for matching vma's. + */ + retval = 0; + vma = vma_next(&vmi); + break; + } + } + + /* + * We need look no further than the maximum address a fragment + * could possibly have landed at. Also cast things to loff_t to + * prevent overflows and make comparisons vs. equal-width types. + */ + size = PAGE_ALIGN(size); + while (vma && (loff_t)(vma->vm_end - addr) <= size) { + /* finding a matching vma now does not alter retval */ + if ((vma->vm_ops == &shm_vm_ops) && + ((vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) && + (vma->vm_file == file)) { + do_vma_munmap(&vmi, vma, vma->vm_start, vma->vm_end, + NULL, false); + } + + vma = vma_next(&vmi); + } + +#else /* CONFIG_MMU */ + vma = vma_lookup(mm, addr); + /* under NOMMU conditions, the exact address to be destroyed must be + * given + */ + if (vma && vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) { + do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start, NULL); + retval = 0; + } + +#endif + + mmap_write_unlock(mm); + return retval; +} + +SYSCALL_DEFINE1(shmdt, char __user *, shmaddr) +{ + return ksys_shmdt(shmaddr); +} + +#ifdef CONFIG_PROC_FS +static int sysvipc_shm_proc_show(struct seq_file *s, void *it) +{ + struct pid_namespace *pid_ns = ipc_seq_pid_ns(s); + struct user_namespace *user_ns = seq_user_ns(s); + struct kern_ipc_perm *ipcp = it; + struct shmid_kernel *shp; + unsigned long rss = 0, swp = 0; + + shp = container_of(ipcp, struct shmid_kernel, shm_perm); + shm_add_rss_swap(shp, &rss, &swp); + +#if BITS_PER_LONG <= 32 +#define SIZE_SPEC "%10lu" +#else +#define SIZE_SPEC "%21lu" +#endif + + seq_printf(s, + "%10d %10d %4o " SIZE_SPEC " %5u %5u " + "%5lu %5u %5u %5u %5u %10llu %10llu %10llu " + SIZE_SPEC " " SIZE_SPEC "\n", + shp->shm_perm.key, + shp->shm_perm.id, + shp->shm_perm.mode, + shp->shm_segsz, + pid_nr_ns(shp->shm_cprid, pid_ns), + pid_nr_ns(shp->shm_lprid, pid_ns), + shp->shm_nattch, + from_kuid_munged(user_ns, shp->shm_perm.uid), + from_kgid_munged(user_ns, shp->shm_perm.gid), + from_kuid_munged(user_ns, shp->shm_perm.cuid), + from_kgid_munged(user_ns, shp->shm_perm.cgid), + shp->shm_atim, + shp->shm_dtim, + shp->shm_ctim, + rss * PAGE_SIZE, + swp * PAGE_SIZE); + + return 0; +} +#endif diff --git a/ipc/syscall.c b/ipc/syscall.c new file mode 100644 index 0000000000..dfb0e988d5 --- /dev/null +++ b/ipc/syscall.c @@ -0,0 +1,211 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * sys_ipc() is the old de-multiplexer for the SysV IPC calls. + * + * This is really horribly ugly, and new architectures should just wire up + * the individual syscalls instead. + */ +#include <linux/unistd.h> +#include <linux/syscalls.h> +#include <linux/security.h> +#include <linux/ipc_namespace.h> +#include "util.h" + +#ifdef __ARCH_WANT_SYS_IPC +#include <linux/errno.h> +#include <linux/ipc.h> +#include <linux/shm.h> +#include <linux/uaccess.h> + +int ksys_ipc(unsigned int call, int first, unsigned long second, + unsigned long third, void __user * ptr, long fifth) +{ + int version, ret; + + version = call >> 16; /* hack for backward compatibility */ + call &= 0xffff; + + switch (call) { + case SEMOP: + return ksys_semtimedop(first, (struct sembuf __user *)ptr, + second, NULL); + case SEMTIMEDOP: + if (IS_ENABLED(CONFIG_64BIT)) + return ksys_semtimedop(first, ptr, second, + (const struct __kernel_timespec __user *)fifth); + else if (IS_ENABLED(CONFIG_COMPAT_32BIT_TIME)) + return compat_ksys_semtimedop(first, ptr, second, + (const struct old_timespec32 __user *)fifth); + else + return -ENOSYS; + + case SEMGET: + return ksys_semget(first, second, third); + case SEMCTL: { + unsigned long arg; + if (!ptr) + return -EINVAL; + if (get_user(arg, (unsigned long __user *) ptr)) + return -EFAULT; + return ksys_old_semctl(first, second, third, arg); + } + + case MSGSND: + return ksys_msgsnd(first, (struct msgbuf __user *) ptr, + second, third); + case MSGRCV: + switch (version) { + case 0: { + struct ipc_kludge tmp; + if (!ptr) + return -EINVAL; + + if (copy_from_user(&tmp, + (struct ipc_kludge __user *) ptr, + sizeof(tmp))) + return -EFAULT; + return ksys_msgrcv(first, tmp.msgp, second, + tmp.msgtyp, third); + } + default: + return ksys_msgrcv(first, + (struct msgbuf __user *) ptr, + second, fifth, third); + } + case MSGGET: + return ksys_msgget((key_t) first, second); + case MSGCTL: + return ksys_old_msgctl(first, second, + (struct msqid_ds __user *)ptr); + + case SHMAT: + switch (version) { + default: { + unsigned long raddr; + ret = do_shmat(first, (char __user *)ptr, + second, &raddr, SHMLBA); + if (ret) + return ret; + return put_user(raddr, (unsigned long __user *) third); + } + case 1: + /* + * This was the entry point for kernel-originating calls + * from iBCS2 in 2.2 days. + */ + return -EINVAL; + } + case SHMDT: + return ksys_shmdt((char __user *)ptr); + case SHMGET: + return ksys_shmget(first, second, third); + case SHMCTL: + return ksys_old_shmctl(first, second, + (struct shmid_ds __user *) ptr); + default: + return -ENOSYS; + } +} + +SYSCALL_DEFINE6(ipc, unsigned int, call, int, first, unsigned long, second, + unsigned long, third, void __user *, ptr, long, fifth) +{ + return ksys_ipc(call, first, second, third, ptr, fifth); +} +#endif + +#ifdef CONFIG_COMPAT +#include <linux/compat.h> + +#ifndef COMPAT_SHMLBA +#define COMPAT_SHMLBA SHMLBA +#endif + +struct compat_ipc_kludge { + compat_uptr_t msgp; + compat_long_t msgtyp; +}; + +#ifdef CONFIG_ARCH_WANT_OLD_COMPAT_IPC +int compat_ksys_ipc(u32 call, int first, int second, + u32 third, compat_uptr_t ptr, u32 fifth) +{ + int version; + u32 pad; + + version = call >> 16; /* hack for backward compatibility */ + call &= 0xffff; + + switch (call) { + case SEMOP: + /* struct sembuf is the same on 32 and 64bit :)) */ + return ksys_semtimedop(first, compat_ptr(ptr), second, NULL); + case SEMTIMEDOP: + if (!IS_ENABLED(CONFIG_COMPAT_32BIT_TIME)) + return -ENOSYS; + return compat_ksys_semtimedop(first, compat_ptr(ptr), second, + compat_ptr(fifth)); + case SEMGET: + return ksys_semget(first, second, third); + case SEMCTL: + if (!ptr) + return -EINVAL; + if (get_user(pad, (u32 __user *) compat_ptr(ptr))) + return -EFAULT; + return compat_ksys_old_semctl(first, second, third, pad); + + case MSGSND: + return compat_ksys_msgsnd(first, ptr, second, third); + + case MSGRCV: { + void __user *uptr = compat_ptr(ptr); + + if (first < 0 || second < 0) + return -EINVAL; + + if (!version) { + struct compat_ipc_kludge ipck; + if (!uptr) + return -EINVAL; + if (copy_from_user(&ipck, uptr, sizeof(ipck))) + return -EFAULT; + return compat_ksys_msgrcv(first, ipck.msgp, second, + ipck.msgtyp, third); + } + return compat_ksys_msgrcv(first, ptr, second, fifth, third); + } + case MSGGET: + return ksys_msgget(first, second); + case MSGCTL: + return compat_ksys_old_msgctl(first, second, compat_ptr(ptr)); + + case SHMAT: { + int err; + unsigned long raddr; + + if (version == 1) + return -EINVAL; + err = do_shmat(first, compat_ptr(ptr), second, &raddr, + COMPAT_SHMLBA); + if (err < 0) + return err; + return put_user(raddr, (compat_ulong_t __user *)compat_ptr(third)); + } + case SHMDT: + return ksys_shmdt(compat_ptr(ptr)); + case SHMGET: + return ksys_shmget(first, (unsigned int)second, third); + case SHMCTL: + return compat_ksys_old_shmctl(first, second, compat_ptr(ptr)); + } + + return -ENOSYS; +} + +COMPAT_SYSCALL_DEFINE6(ipc, u32, call, int, first, int, second, + u32, third, compat_uptr_t, ptr, u32, fifth) +{ + return compat_ksys_ipc(call, first, second, third, ptr, fifth); +} +#endif +#endif diff --git a/ipc/util.c b/ipc/util.c new file mode 100644 index 0000000000..05cb9de667 --- /dev/null +++ b/ipc/util.c @@ -0,0 +1,931 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/ipc/util.c + * Copyright (C) 1992 Krishna Balasubramanian + * + * Sep 1997 - Call suser() last after "normal" permission checks so we + * get BSD style process accounting right. + * Occurs in several places in the IPC code. + * Chris Evans, <chris@ferret.lmh.ox.ac.uk> + * Nov 1999 - ipc helper functions, unified SMP locking + * Manfred Spraul <manfred@colorfullife.com> + * Oct 2002 - One lock per IPC id. RCU ipc_free for lock-free grow_ary(). + * Mingming Cao <cmm@us.ibm.com> + * Mar 2006 - support for audit of ipc object properties + * Dustin Kirkland <dustin.kirkland@us.ibm.com> + * Jun 2006 - namespaces ssupport + * OpenVZ, SWsoft Inc. + * Pavel Emelianov <xemul@openvz.org> + * + * General sysv ipc locking scheme: + * rcu_read_lock() + * obtain the ipc object (kern_ipc_perm) by looking up the id in an idr + * tree. + * - perform initial checks (capabilities, auditing and permission, + * etc). + * - perform read-only operations, such as INFO command, that + * do not demand atomicity + * acquire the ipc lock (kern_ipc_perm.lock) through + * ipc_lock_object() + * - perform read-only operations that demand atomicity, + * such as STAT command. + * - perform data updates, such as SET, RMID commands and + * mechanism-specific operations (semop/semtimedop, + * msgsnd/msgrcv, shmat/shmdt). + * drop the ipc lock, through ipc_unlock_object(). + * rcu_read_unlock() + * + * The ids->rwsem must be taken when: + * - creating, removing and iterating the existing entries in ipc + * identifier sets. + * - iterating through files under /proc/sysvipc/ + * + * Note that sems have a special fast path that avoids kern_ipc_perm.lock - + * see sem_lock(). + */ + +#include <linux/mm.h> +#include <linux/shm.h> +#include <linux/init.h> +#include <linux/msg.h> +#include <linux/vmalloc.h> +#include <linux/slab.h> +#include <linux/notifier.h> +#include <linux/capability.h> +#include <linux/highuid.h> +#include <linux/security.h> +#include <linux/rcupdate.h> +#include <linux/workqueue.h> +#include <linux/seq_file.h> +#include <linux/proc_fs.h> +#include <linux/audit.h> +#include <linux/nsproxy.h> +#include <linux/rwsem.h> +#include <linux/memory.h> +#include <linux/ipc_namespace.h> +#include <linux/rhashtable.h> +#include <linux/log2.h> + +#include <asm/unistd.h> + +#include "util.h" + +struct ipc_proc_iface { + const char *path; + const char *header; + int ids; + int (*show)(struct seq_file *, void *); +}; + +/** + * ipc_init - initialise ipc subsystem + * + * The various sysv ipc resources (semaphores, messages and shared + * memory) are initialised. + * + * A callback routine is registered into the memory hotplug notifier + * chain: since msgmni scales to lowmem this callback routine will be + * called upon successful memory add / remove to recompute msmgni. + */ +static int __init ipc_init(void) +{ + proc_mkdir("sysvipc", NULL); + sem_init(); + msg_init(); + shm_init(); + + return 0; +} +device_initcall(ipc_init); + +static const struct rhashtable_params ipc_kht_params = { + .head_offset = offsetof(struct kern_ipc_perm, khtnode), + .key_offset = offsetof(struct kern_ipc_perm, key), + .key_len = sizeof_field(struct kern_ipc_perm, key), + .automatic_shrinking = true, +}; + +/** + * ipc_init_ids - initialise ipc identifiers + * @ids: ipc identifier set + * + * Set up the sequence range to use for the ipc identifier range (limited + * below ipc_mni) then initialise the keys hashtable and ids idr. + */ +void ipc_init_ids(struct ipc_ids *ids) +{ + ids->in_use = 0; + ids->seq = 0; + init_rwsem(&ids->rwsem); + rhashtable_init(&ids->key_ht, &ipc_kht_params); + idr_init(&ids->ipcs_idr); + ids->max_idx = -1; + ids->last_idx = -1; +#ifdef CONFIG_CHECKPOINT_RESTORE + ids->next_id = -1; +#endif +} + +#ifdef CONFIG_PROC_FS +static const struct proc_ops sysvipc_proc_ops; +/** + * ipc_init_proc_interface - create a proc interface for sysipc types using a seq_file interface. + * @path: Path in procfs + * @header: Banner to be printed at the beginning of the file. + * @ids: ipc id table to iterate. + * @show: show routine. + */ +void __init ipc_init_proc_interface(const char *path, const char *header, + int ids, int (*show)(struct seq_file *, void *)) +{ + struct proc_dir_entry *pde; + struct ipc_proc_iface *iface; + + iface = kmalloc(sizeof(*iface), GFP_KERNEL); + if (!iface) + return; + iface->path = path; + iface->header = header; + iface->ids = ids; + iface->show = show; + + pde = proc_create_data(path, + S_IRUGO, /* world readable */ + NULL, /* parent dir */ + &sysvipc_proc_ops, + iface); + if (!pde) + kfree(iface); +} +#endif + +/** + * ipc_findkey - find a key in an ipc identifier set + * @ids: ipc identifier set + * @key: key to find + * + * Returns the locked pointer to the ipc structure if found or NULL + * otherwise. If key is found ipc points to the owning ipc structure + * + * Called with writer ipc_ids.rwsem held. + */ +static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key) +{ + struct kern_ipc_perm *ipcp; + + ipcp = rhashtable_lookup_fast(&ids->key_ht, &key, + ipc_kht_params); + if (!ipcp) + return NULL; + + rcu_read_lock(); + ipc_lock_object(ipcp); + return ipcp; +} + +/* + * Insert new IPC object into idr tree, and set sequence number and id + * in the correct order. + * Especially: + * - the sequence number must be set before inserting the object into the idr, + * because the sequence number is accessed without a lock. + * - the id can/must be set after inserting the object into the idr. + * All accesses must be done after getting kern_ipc_perm.lock. + * + * The caller must own kern_ipc_perm.lock.of the new object. + * On error, the function returns a (negative) error code. + * + * To conserve sequence number space, especially with extended ipc_mni, + * the sequence number is incremented only when the returned ID is less than + * the last one. + */ +static inline int ipc_idr_alloc(struct ipc_ids *ids, struct kern_ipc_perm *new) +{ + int idx, next_id = -1; + +#ifdef CONFIG_CHECKPOINT_RESTORE + next_id = ids->next_id; + ids->next_id = -1; +#endif + + /* + * As soon as a new object is inserted into the idr, + * ipc_obtain_object_idr() or ipc_obtain_object_check() can find it, + * and the lockless preparations for ipc operations can start. + * This means especially: permission checks, audit calls, allocation + * of undo structures, ... + * + * Thus the object must be fully initialized, and if something fails, + * then the full tear-down sequence must be followed. + * (i.e.: set new->deleted, reduce refcount, call_rcu()) + */ + + if (next_id < 0) { /* !CHECKPOINT_RESTORE or next_id is unset */ + int max_idx; + + max_idx = max(ids->in_use*3/2, ipc_min_cycle); + max_idx = min(max_idx, ipc_mni); + + /* allocate the idx, with a NULL struct kern_ipc_perm */ + idx = idr_alloc_cyclic(&ids->ipcs_idr, NULL, 0, max_idx, + GFP_NOWAIT); + + if (idx >= 0) { + /* + * idx got allocated successfully. + * Now calculate the sequence number and set the + * pointer for real. + */ + if (idx <= ids->last_idx) { + ids->seq++; + if (ids->seq >= ipcid_seq_max()) + ids->seq = 0; + } + ids->last_idx = idx; + + new->seq = ids->seq; + /* no need for smp_wmb(), this is done + * inside idr_replace, as part of + * rcu_assign_pointer + */ + idr_replace(&ids->ipcs_idr, new, idx); + } + } else { + new->seq = ipcid_to_seqx(next_id); + idx = idr_alloc(&ids->ipcs_idr, new, ipcid_to_idx(next_id), + 0, GFP_NOWAIT); + } + if (idx >= 0) + new->id = (new->seq << ipcmni_seq_shift()) + idx; + return idx; +} + +/** + * ipc_addid - add an ipc identifier + * @ids: ipc identifier set + * @new: new ipc permission set + * @limit: limit for the number of used ids + * + * Add an entry 'new' to the ipc ids idr. The permissions object is + * initialised and the first free entry is set up and the index assigned + * is returned. The 'new' entry is returned in a locked state on success. + * + * On failure the entry is not locked and a negative err-code is returned. + * The caller must use ipc_rcu_putref() to free the identifier. + * + * Called with writer ipc_ids.rwsem held. + */ +int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int limit) +{ + kuid_t euid; + kgid_t egid; + int idx, err; + + /* 1) Initialize the refcount so that ipc_rcu_putref works */ + refcount_set(&new->refcount, 1); + + if (limit > ipc_mni) + limit = ipc_mni; + + if (ids->in_use >= limit) + return -ENOSPC; + + idr_preload(GFP_KERNEL); + + spin_lock_init(&new->lock); + rcu_read_lock(); + spin_lock(&new->lock); + + current_euid_egid(&euid, &egid); + new->cuid = new->uid = euid; + new->gid = new->cgid = egid; + + new->deleted = false; + + idx = ipc_idr_alloc(ids, new); + idr_preload_end(); + + if (idx >= 0 && new->key != IPC_PRIVATE) { + err = rhashtable_insert_fast(&ids->key_ht, &new->khtnode, + ipc_kht_params); + if (err < 0) { + idr_remove(&ids->ipcs_idr, idx); + idx = err; + } + } + if (idx < 0) { + new->deleted = true; + spin_unlock(&new->lock); + rcu_read_unlock(); + return idx; + } + + ids->in_use++; + if (idx > ids->max_idx) + ids->max_idx = idx; + return idx; +} + +/** + * ipcget_new - create a new ipc object + * @ns: ipc namespace + * @ids: ipc identifier set + * @ops: the actual creation routine to call + * @params: its parameters + * + * This routine is called by sys_msgget, sys_semget() and sys_shmget() + * when the key is IPC_PRIVATE. + */ +static int ipcget_new(struct ipc_namespace *ns, struct ipc_ids *ids, + const struct ipc_ops *ops, struct ipc_params *params) +{ + int err; + + down_write(&ids->rwsem); + err = ops->getnew(ns, params); + up_write(&ids->rwsem); + return err; +} + +/** + * ipc_check_perms - check security and permissions for an ipc object + * @ns: ipc namespace + * @ipcp: ipc permission set + * @ops: the actual security routine to call + * @params: its parameters + * + * This routine is called by sys_msgget(), sys_semget() and sys_shmget() + * when the key is not IPC_PRIVATE and that key already exists in the + * ds IDR. + * + * On success, the ipc id is returned. + * + * It is called with ipc_ids.rwsem and ipcp->lock held. + */ +static int ipc_check_perms(struct ipc_namespace *ns, + struct kern_ipc_perm *ipcp, + const struct ipc_ops *ops, + struct ipc_params *params) +{ + int err; + + if (ipcperms(ns, ipcp, params->flg)) + err = -EACCES; + else { + err = ops->associate(ipcp, params->flg); + if (!err) + err = ipcp->id; + } + + return err; +} + +/** + * ipcget_public - get an ipc object or create a new one + * @ns: ipc namespace + * @ids: ipc identifier set + * @ops: the actual creation routine to call + * @params: its parameters + * + * This routine is called by sys_msgget, sys_semget() and sys_shmget() + * when the key is not IPC_PRIVATE. + * It adds a new entry if the key is not found and does some permission + * / security checkings if the key is found. + * + * On success, the ipc id is returned. + */ +static int ipcget_public(struct ipc_namespace *ns, struct ipc_ids *ids, + const struct ipc_ops *ops, struct ipc_params *params) +{ + struct kern_ipc_perm *ipcp; + int flg = params->flg; + int err; + + /* + * Take the lock as a writer since we are potentially going to add + * a new entry + read locks are not "upgradable" + */ + down_write(&ids->rwsem); + ipcp = ipc_findkey(ids, params->key); + if (ipcp == NULL) { + /* key not used */ + if (!(flg & IPC_CREAT)) + err = -ENOENT; + else + err = ops->getnew(ns, params); + } else { + /* ipc object has been locked by ipc_findkey() */ + + if (flg & IPC_CREAT && flg & IPC_EXCL) + err = -EEXIST; + else { + err = 0; + if (ops->more_checks) + err = ops->more_checks(ipcp, params); + if (!err) + /* + * ipc_check_perms returns the IPC id on + * success + */ + err = ipc_check_perms(ns, ipcp, ops, params); + } + ipc_unlock(ipcp); + } + up_write(&ids->rwsem); + + return err; +} + +/** + * ipc_kht_remove - remove an ipc from the key hashtable + * @ids: ipc identifier set + * @ipcp: ipc perm structure containing the key to remove + * + * ipc_ids.rwsem (as a writer) and the spinlock for this ID are held + * before this function is called, and remain locked on the exit. + */ +static void ipc_kht_remove(struct ipc_ids *ids, struct kern_ipc_perm *ipcp) +{ + if (ipcp->key != IPC_PRIVATE) + WARN_ON_ONCE(rhashtable_remove_fast(&ids->key_ht, &ipcp->khtnode, + ipc_kht_params)); +} + +/** + * ipc_search_maxidx - search for the highest assigned index + * @ids: ipc identifier set + * @limit: known upper limit for highest assigned index + * + * The function determines the highest assigned index in @ids. It is intended + * to be called when ids->max_idx needs to be updated. + * Updating ids->max_idx is necessary when the current highest index ipc + * object is deleted. + * If no ipc object is allocated, then -1 is returned. + * + * ipc_ids.rwsem needs to be held by the caller. + */ +static int ipc_search_maxidx(struct ipc_ids *ids, int limit) +{ + int tmpidx; + int i; + int retval; + + i = ilog2(limit+1); + + retval = 0; + for (; i >= 0; i--) { + tmpidx = retval | (1<<i); + /* + * "0" is a possible index value, thus search using + * e.g. 15,7,3,1,0 instead of 16,8,4,2,1. + */ + tmpidx = tmpidx-1; + if (idr_get_next(&ids->ipcs_idr, &tmpidx)) + retval |= (1<<i); + } + return retval - 1; +} + +/** + * ipc_rmid - remove an ipc identifier + * @ids: ipc identifier set + * @ipcp: ipc perm structure containing the identifier to remove + * + * ipc_ids.rwsem (as a writer) and the spinlock for this ID are held + * before this function is called, and remain locked on the exit. + */ +void ipc_rmid(struct ipc_ids *ids, struct kern_ipc_perm *ipcp) +{ + int idx = ipcid_to_idx(ipcp->id); + + WARN_ON_ONCE(idr_remove(&ids->ipcs_idr, idx) != ipcp); + ipc_kht_remove(ids, ipcp); + ids->in_use--; + ipcp->deleted = true; + + if (unlikely(idx == ids->max_idx)) { + idx = ids->max_idx-1; + if (idx >= 0) + idx = ipc_search_maxidx(ids, idx); + ids->max_idx = idx; + } +} + +/** + * ipc_set_key_private - switch the key of an existing ipc to IPC_PRIVATE + * @ids: ipc identifier set + * @ipcp: ipc perm structure containing the key to modify + * + * ipc_ids.rwsem (as a writer) and the spinlock for this ID are held + * before this function is called, and remain locked on the exit. + */ +void ipc_set_key_private(struct ipc_ids *ids, struct kern_ipc_perm *ipcp) +{ + ipc_kht_remove(ids, ipcp); + ipcp->key = IPC_PRIVATE; +} + +bool ipc_rcu_getref(struct kern_ipc_perm *ptr) +{ + return refcount_inc_not_zero(&ptr->refcount); +} + +void ipc_rcu_putref(struct kern_ipc_perm *ptr, + void (*func)(struct rcu_head *head)) +{ + if (!refcount_dec_and_test(&ptr->refcount)) + return; + + call_rcu(&ptr->rcu, func); +} + +/** + * ipcperms - check ipc permissions + * @ns: ipc namespace + * @ipcp: ipc permission set + * @flag: desired permission set + * + * Check user, group, other permissions for access + * to ipc resources. return 0 if allowed + * + * @flag will most probably be 0 or ``S_...UGO`` from <linux/stat.h> + */ +int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flag) +{ + kuid_t euid = current_euid(); + int requested_mode, granted_mode; + + audit_ipc_obj(ipcp); + requested_mode = (flag >> 6) | (flag >> 3) | flag; + granted_mode = ipcp->mode; + if (uid_eq(euid, ipcp->cuid) || + uid_eq(euid, ipcp->uid)) + granted_mode >>= 6; + else if (in_group_p(ipcp->cgid) || in_group_p(ipcp->gid)) + granted_mode >>= 3; + /* is there some bit set in requested_mode but not in granted_mode? */ + if ((requested_mode & ~granted_mode & 0007) && + !ns_capable(ns->user_ns, CAP_IPC_OWNER)) + return -1; + + return security_ipc_permission(ipcp, flag); +} + +/* + * Functions to convert between the kern_ipc_perm structure and the + * old/new ipc_perm structures + */ + +/** + * kernel_to_ipc64_perm - convert kernel ipc permissions to user + * @in: kernel permissions + * @out: new style ipc permissions + * + * Turn the kernel object @in into a set of permissions descriptions + * for returning to userspace (@out). + */ +void kernel_to_ipc64_perm(struct kern_ipc_perm *in, struct ipc64_perm *out) +{ + out->key = in->key; + out->uid = from_kuid_munged(current_user_ns(), in->uid); + out->gid = from_kgid_munged(current_user_ns(), in->gid); + out->cuid = from_kuid_munged(current_user_ns(), in->cuid); + out->cgid = from_kgid_munged(current_user_ns(), in->cgid); + out->mode = in->mode; + out->seq = in->seq; +} + +/** + * ipc64_perm_to_ipc_perm - convert new ipc permissions to old + * @in: new style ipc permissions + * @out: old style ipc permissions + * + * Turn the new style permissions object @in into a compatibility + * object and store it into the @out pointer. + */ +void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out) +{ + out->key = in->key; + SET_UID(out->uid, in->uid); + SET_GID(out->gid, in->gid); + SET_UID(out->cuid, in->cuid); + SET_GID(out->cgid, in->cgid); + out->mode = in->mode; + out->seq = in->seq; +} + +/** + * ipc_obtain_object_idr + * @ids: ipc identifier set + * @id: ipc id to look for + * + * Look for an id in the ipc ids idr and return associated ipc object. + * + * Call inside the RCU critical section. + * The ipc object is *not* locked on exit. + */ +struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id) +{ + struct kern_ipc_perm *out; + int idx = ipcid_to_idx(id); + + out = idr_find(&ids->ipcs_idr, idx); + if (!out) + return ERR_PTR(-EINVAL); + + return out; +} + +/** + * ipc_obtain_object_check + * @ids: ipc identifier set + * @id: ipc id to look for + * + * Similar to ipc_obtain_object_idr() but also checks the ipc object + * sequence number. + * + * Call inside the RCU critical section. + * The ipc object is *not* locked on exit. + */ +struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id) +{ + struct kern_ipc_perm *out = ipc_obtain_object_idr(ids, id); + + if (IS_ERR(out)) + goto out; + + if (ipc_checkid(out, id)) + return ERR_PTR(-EINVAL); +out: + return out; +} + +/** + * ipcget - Common sys_*get() code + * @ns: namespace + * @ids: ipc identifier set + * @ops: operations to be called on ipc object creation, permission checks + * and further checks + * @params: the parameters needed by the previous operations. + * + * Common routine called by sys_msgget(), sys_semget() and sys_shmget(). + */ +int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids, + const struct ipc_ops *ops, struct ipc_params *params) +{ + if (params->key == IPC_PRIVATE) + return ipcget_new(ns, ids, ops, params); + else + return ipcget_public(ns, ids, ops, params); +} + +/** + * ipc_update_perm - update the permissions of an ipc object + * @in: the permission given as input. + * @out: the permission of the ipc to set. + */ +int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out) +{ + kuid_t uid = make_kuid(current_user_ns(), in->uid); + kgid_t gid = make_kgid(current_user_ns(), in->gid); + if (!uid_valid(uid) || !gid_valid(gid)) + return -EINVAL; + + out->uid = uid; + out->gid = gid; + out->mode = (out->mode & ~S_IRWXUGO) + | (in->mode & S_IRWXUGO); + + return 0; +} + +/** + * ipcctl_obtain_check - retrieve an ipc object and check permissions + * @ns: ipc namespace + * @ids: the table of ids where to look for the ipc + * @id: the id of the ipc to retrieve + * @cmd: the cmd to check + * @perm: the permission to set + * @extra_perm: one extra permission parameter used by msq + * + * This function does some common audit and permissions check for some IPC_XXX + * cmd and is called from semctl_down, shmctl_down and msgctl_down. + * + * It: + * - retrieves the ipc object with the given id in the given table. + * - performs some audit and permission check, depending on the given cmd + * - returns a pointer to the ipc object or otherwise, the corresponding + * error. + * + * Call holding the both the rwsem and the rcu read lock. + */ +struct kern_ipc_perm *ipcctl_obtain_check(struct ipc_namespace *ns, + struct ipc_ids *ids, int id, int cmd, + struct ipc64_perm *perm, int extra_perm) +{ + kuid_t euid; + int err = -EPERM; + struct kern_ipc_perm *ipcp; + + ipcp = ipc_obtain_object_check(ids, id); + if (IS_ERR(ipcp)) { + err = PTR_ERR(ipcp); + goto err; + } + + audit_ipc_obj(ipcp); + if (cmd == IPC_SET) + audit_ipc_set_perm(extra_perm, perm->uid, + perm->gid, perm->mode); + + euid = current_euid(); + if (uid_eq(euid, ipcp->cuid) || uid_eq(euid, ipcp->uid) || + ns_capable(ns->user_ns, CAP_SYS_ADMIN)) + return ipcp; /* successful lookup */ +err: + return ERR_PTR(err); +} + +#ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION + + +/** + * ipc_parse_version - ipc call version + * @cmd: pointer to command + * + * Return IPC_64 for new style IPC and IPC_OLD for old style IPC. + * The @cmd value is turned from an encoding command and version into + * just the command code. + */ +int ipc_parse_version(int *cmd) +{ + if (*cmd & IPC_64) { + *cmd ^= IPC_64; + return IPC_64; + } else { + return IPC_OLD; + } +} + +#endif /* CONFIG_ARCH_WANT_IPC_PARSE_VERSION */ + +#ifdef CONFIG_PROC_FS +struct ipc_proc_iter { + struct ipc_namespace *ns; + struct pid_namespace *pid_ns; + struct ipc_proc_iface *iface; +}; + +struct pid_namespace *ipc_seq_pid_ns(struct seq_file *s) +{ + struct ipc_proc_iter *iter = s->private; + return iter->pid_ns; +} + +/** + * sysvipc_find_ipc - Find and lock the ipc structure based on seq pos + * @ids: ipc identifier set + * @pos: expected position + * + * The function finds an ipc structure, based on the sequence file + * position @pos. If there is no ipc structure at position @pos, then + * the successor is selected. + * If a structure is found, then it is locked (both rcu_read_lock() and + * ipc_lock_object()) and @pos is set to the position needed to locate + * the found ipc structure. + * If nothing is found (i.e. EOF), @pos is not modified. + * + * The function returns the found ipc structure, or NULL at EOF. + */ +static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t *pos) +{ + int tmpidx; + struct kern_ipc_perm *ipc; + + /* convert from position to idr index -> "-1" */ + tmpidx = *pos - 1; + + ipc = idr_get_next(&ids->ipcs_idr, &tmpidx); + if (ipc != NULL) { + rcu_read_lock(); + ipc_lock_object(ipc); + + /* convert from idr index to position -> "+1" */ + *pos = tmpidx + 1; + } + return ipc; +} + +static void *sysvipc_proc_next(struct seq_file *s, void *it, loff_t *pos) +{ + struct ipc_proc_iter *iter = s->private; + struct ipc_proc_iface *iface = iter->iface; + struct kern_ipc_perm *ipc = it; + + /* If we had an ipc id locked before, unlock it */ + if (ipc && ipc != SEQ_START_TOKEN) + ipc_unlock(ipc); + + /* Next -> search for *pos+1 */ + (*pos)++; + return sysvipc_find_ipc(&iter->ns->ids[iface->ids], pos); +} + +/* + * File positions: pos 0 -> header, pos n -> ipc idx = n - 1. + * SeqFile iterator: iterator value locked ipc pointer or SEQ_TOKEN_START. + */ +static void *sysvipc_proc_start(struct seq_file *s, loff_t *pos) +{ + struct ipc_proc_iter *iter = s->private; + struct ipc_proc_iface *iface = iter->iface; + struct ipc_ids *ids; + + ids = &iter->ns->ids[iface->ids]; + + /* + * Take the lock - this will be released by the corresponding + * call to stop(). + */ + down_read(&ids->rwsem); + + /* pos < 0 is invalid */ + if (*pos < 0) + return NULL; + + /* pos == 0 means header */ + if (*pos == 0) + return SEQ_START_TOKEN; + + /* Otherwise return the correct ipc structure */ + return sysvipc_find_ipc(ids, pos); +} + +static void sysvipc_proc_stop(struct seq_file *s, void *it) +{ + struct kern_ipc_perm *ipc = it; + struct ipc_proc_iter *iter = s->private; + struct ipc_proc_iface *iface = iter->iface; + struct ipc_ids *ids; + + /* If we had a locked structure, release it */ + if (ipc && ipc != SEQ_START_TOKEN) + ipc_unlock(ipc); + + ids = &iter->ns->ids[iface->ids]; + /* Release the lock we took in start() */ + up_read(&ids->rwsem); +} + +static int sysvipc_proc_show(struct seq_file *s, void *it) +{ + struct ipc_proc_iter *iter = s->private; + struct ipc_proc_iface *iface = iter->iface; + + if (it == SEQ_START_TOKEN) { + seq_puts(s, iface->header); + return 0; + } + + return iface->show(s, it); +} + +static const struct seq_operations sysvipc_proc_seqops = { + .start = sysvipc_proc_start, + .stop = sysvipc_proc_stop, + .next = sysvipc_proc_next, + .show = sysvipc_proc_show, +}; + +static int sysvipc_proc_open(struct inode *inode, struct file *file) +{ + struct ipc_proc_iter *iter; + + iter = __seq_open_private(file, &sysvipc_proc_seqops, sizeof(*iter)); + if (!iter) + return -ENOMEM; + + iter->iface = pde_data(inode); + iter->ns = get_ipc_ns(current->nsproxy->ipc_ns); + iter->pid_ns = get_pid_ns(task_active_pid_ns(current)); + + return 0; +} + +static int sysvipc_proc_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct ipc_proc_iter *iter = seq->private; + put_ipc_ns(iter->ns); + put_pid_ns(iter->pid_ns); + return seq_release_private(inode, file); +} + +static const struct proc_ops sysvipc_proc_ops = { + .proc_flags = PROC_ENTRY_PERMANENT, + .proc_open = sysvipc_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = sysvipc_proc_release, +}; +#endif /* CONFIG_PROC_FS */ diff --git a/ipc/util.h b/ipc/util.h new file mode 100644 index 0000000000..67bdd2aa2c --- /dev/null +++ b/ipc/util.h @@ -0,0 +1,291 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * linux/ipc/util.h + * Copyright (C) 1999 Christoph Rohland + * + * ipc helper functions (c) 1999 Manfred Spraul <manfred@colorfullife.com> + * namespaces support. 2006 OpenVZ, SWsoft Inc. + * Pavel Emelianov <xemul@openvz.org> + */ + +#ifndef _IPC_UTIL_H +#define _IPC_UTIL_H + +#include <linux/unistd.h> +#include <linux/err.h> +#include <linux/ipc_namespace.h> + +/* + * The IPC ID contains 2 separate numbers - index and sequence number. + * By default, + * bits 0-14: index (32k, 15 bits) + * bits 15-30: sequence number (64k, 16 bits) + * + * When IPCMNI extension mode is turned on, the composition changes: + * bits 0-23: index (16M, 24 bits) + * bits 24-30: sequence number (128, 7 bits) + */ +#define IPCMNI_SHIFT 15 +#define IPCMNI_EXTEND_SHIFT 24 +#define IPCMNI_EXTEND_MIN_CYCLE (RADIX_TREE_MAP_SIZE * RADIX_TREE_MAP_SIZE) +#define IPCMNI (1 << IPCMNI_SHIFT) +#define IPCMNI_EXTEND (1 << IPCMNI_EXTEND_SHIFT) + +#ifdef CONFIG_SYSVIPC_SYSCTL +extern int ipc_mni; +extern int ipc_mni_shift; +extern int ipc_min_cycle; + +#define ipcmni_seq_shift() ipc_mni_shift +#define IPCMNI_IDX_MASK ((1 << ipc_mni_shift) - 1) + +#else /* CONFIG_SYSVIPC_SYSCTL */ + +#define ipc_mni IPCMNI +#define ipc_min_cycle ((int)RADIX_TREE_MAP_SIZE) +#define ipcmni_seq_shift() IPCMNI_SHIFT +#define IPCMNI_IDX_MASK ((1 << IPCMNI_SHIFT) - 1) +#endif /* CONFIG_SYSVIPC_SYSCTL */ + +void sem_init(void); +void msg_init(void); +void shm_init(void); + +struct ipc_namespace; +struct pid_namespace; + +#ifdef CONFIG_POSIX_MQUEUE +extern void mq_clear_sbinfo(struct ipc_namespace *ns); +#else +static inline void mq_clear_sbinfo(struct ipc_namespace *ns) { } +#endif + +#ifdef CONFIG_SYSVIPC +void sem_init_ns(struct ipc_namespace *ns); +int msg_init_ns(struct ipc_namespace *ns); +void shm_init_ns(struct ipc_namespace *ns); + +void sem_exit_ns(struct ipc_namespace *ns); +void msg_exit_ns(struct ipc_namespace *ns); +void shm_exit_ns(struct ipc_namespace *ns); +#else +static inline void sem_init_ns(struct ipc_namespace *ns) { } +static inline int msg_init_ns(struct ipc_namespace *ns) { return 0; } +static inline void shm_init_ns(struct ipc_namespace *ns) { } + +static inline void sem_exit_ns(struct ipc_namespace *ns) { } +static inline void msg_exit_ns(struct ipc_namespace *ns) { } +static inline void shm_exit_ns(struct ipc_namespace *ns) { } +#endif + +/* + * Structure that holds the parameters needed by the ipc operations + * (see after) + */ +struct ipc_params { + key_t key; + int flg; + union { + size_t size; /* for shared memories */ + int nsems; /* for semaphores */ + } u; /* holds the getnew() specific param */ +}; + +/* + * Structure that holds some ipc operations. This structure is used to unify + * the calls to sys_msgget(), sys_semget(), sys_shmget() + * . routine to call to create a new ipc object. Can be one of newque, + * newary, newseg + * . routine to call to check permissions for a new ipc object. + * Can be one of security_msg_associate, security_sem_associate, + * security_shm_associate + * . routine to call for an extra check if needed + */ +struct ipc_ops { + int (*getnew)(struct ipc_namespace *, struct ipc_params *); + int (*associate)(struct kern_ipc_perm *, int); + int (*more_checks)(struct kern_ipc_perm *, struct ipc_params *); +}; + +struct seq_file; +struct ipc_ids; + +void ipc_init_ids(struct ipc_ids *ids); +#ifdef CONFIG_PROC_FS +void __init ipc_init_proc_interface(const char *path, const char *header, + int ids, int (*show)(struct seq_file *, void *)); +struct pid_namespace *ipc_seq_pid_ns(struct seq_file *); +#else +#define ipc_init_proc_interface(path, header, ids, show) do {} while (0) +#endif + +#define IPC_SEM_IDS 0 +#define IPC_MSG_IDS 1 +#define IPC_SHM_IDS 2 + +#define ipcid_to_idx(id) ((id) & IPCMNI_IDX_MASK) +#define ipcid_to_seqx(id) ((id) >> ipcmni_seq_shift()) +#define ipcid_seq_max() (INT_MAX >> ipcmni_seq_shift()) + +/* must be called with ids->rwsem acquired for writing */ +int ipc_addid(struct ipc_ids *, struct kern_ipc_perm *, int); + +/* must be called with both locks acquired. */ +void ipc_rmid(struct ipc_ids *, struct kern_ipc_perm *); + +/* must be called with both locks acquired. */ +void ipc_set_key_private(struct ipc_ids *, struct kern_ipc_perm *); + +/* must be called with ipcp locked */ +int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flg); + +/** + * ipc_get_maxidx - get the highest assigned index + * @ids: ipc identifier set + * + * The function returns the highest assigned index for @ids. The function + * doesn't scan the idr tree, it uses a cached value. + * + * Called with ipc_ids.rwsem held for reading. + */ +static inline int ipc_get_maxidx(struct ipc_ids *ids) +{ + if (ids->in_use == 0) + return -1; + + if (ids->in_use == ipc_mni) + return ipc_mni - 1; + + return ids->max_idx; +} + +/* + * For allocation that need to be freed by RCU. + * Objects are reference counted, they start with reference count 1. + * getref increases the refcount, the putref call that reduces the recount + * to 0 schedules the rcu destruction. Caller must guarantee locking. + * + * refcount is initialized by ipc_addid(), before that point call_rcu() + * must be used. + */ +bool ipc_rcu_getref(struct kern_ipc_perm *ptr); +void ipc_rcu_putref(struct kern_ipc_perm *ptr, + void (*func)(struct rcu_head *head)); + +struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id); + +void kernel_to_ipc64_perm(struct kern_ipc_perm *in, struct ipc64_perm *out); +void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out); +int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out); +struct kern_ipc_perm *ipcctl_obtain_check(struct ipc_namespace *ns, + struct ipc_ids *ids, int id, int cmd, + struct ipc64_perm *perm, int extra_perm); + +static inline void ipc_update_pid(struct pid **pos, struct pid *pid) +{ + struct pid *old = *pos; + if (old != pid) { + *pos = get_pid(pid); + put_pid(old); + } +} + +#ifdef CONFIG_ARCH_WANT_IPC_PARSE_VERSION +int ipc_parse_version(int *cmd); +#endif + +extern void free_msg(struct msg_msg *msg); +extern struct msg_msg *load_msg(const void __user *src, size_t len); +extern struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst); +extern int store_msg(void __user *dest, struct msg_msg *msg, size_t len); + +static inline int ipc_checkid(struct kern_ipc_perm *ipcp, int id) +{ + return ipcid_to_seqx(id) != ipcp->seq; +} + +static inline void ipc_lock_object(struct kern_ipc_perm *perm) +{ + spin_lock(&perm->lock); +} + +static inline void ipc_unlock_object(struct kern_ipc_perm *perm) +{ + spin_unlock(&perm->lock); +} + +static inline void ipc_assert_locked_object(struct kern_ipc_perm *perm) +{ + assert_spin_locked(&perm->lock); +} + +static inline void ipc_unlock(struct kern_ipc_perm *perm) +{ + ipc_unlock_object(perm); + rcu_read_unlock(); +} + +/* + * ipc_valid_object() - helper to sort out IPC_RMID races for codepaths + * where the respective ipc_ids.rwsem is not being held down. + * Checks whether the ipc object is still around or if it's gone already, as + * ipc_rmid() may have already freed the ID while the ipc lock was spinning. + * Needs to be called with kern_ipc_perm.lock held -- exception made for one + * checkpoint case at sys_semtimedop() as noted in code commentary. + */ +static inline bool ipc_valid_object(struct kern_ipc_perm *perm) +{ + return !perm->deleted; +} + +struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id); +int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids, + const struct ipc_ops *ops, struct ipc_params *params); +void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids, + void (*free)(struct ipc_namespace *, struct kern_ipc_perm *)); + +static inline int sem_check_semmni(struct ipc_namespace *ns) { + /* + * Check semmni range [0, ipc_mni] + * semmni is the last element of sem_ctls[4] array + */ + return ((ns->sem_ctls[3] < 0) || (ns->sem_ctls[3] > ipc_mni)) + ? -ERANGE : 0; +} + +#ifdef CONFIG_COMPAT +#include <linux/compat.h> +struct compat_ipc_perm { + key_t key; + __compat_uid_t uid; + __compat_gid_t gid; + __compat_uid_t cuid; + __compat_gid_t cgid; + compat_mode_t mode; + unsigned short seq; +}; + +void to_compat_ipc_perm(struct compat_ipc_perm *, struct ipc64_perm *); +void to_compat_ipc64_perm(struct compat_ipc64_perm *, struct ipc64_perm *); +int get_compat_ipc_perm(struct ipc64_perm *, struct compat_ipc_perm __user *); +int get_compat_ipc64_perm(struct ipc64_perm *, + struct compat_ipc64_perm __user *); + +static inline int compat_ipc_parse_version(int *cmd) +{ + int version = *cmd & IPC_64; + *cmd &= ~IPC_64; + return version; +} + +long compat_ksys_old_semctl(int semid, int semnum, int cmd, int arg); +long compat_ksys_old_msgctl(int msqid, int cmd, void __user *uptr); +long compat_ksys_msgrcv(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, + compat_long_t msgtyp, int msgflg); +long compat_ksys_msgsnd(int msqid, compat_uptr_t msgp, + compat_ssize_t msgsz, int msgflg); +long compat_ksys_old_shmctl(int shmid, int cmd, void __user *uptr); + +#endif + +#endif |