1 files changed, 75 insertions, 80 deletions

diff --git a/ipc/sem.c b/ipc/sem.c
index 947dc2348271..9e70cd7a17da 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -87,24 +87,6 @@
 #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).
-	 */
-	int	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*/
-	time_t	sem_otime;	/* candidate for sem_otime */
-} ____cacheline_aligned_in_smp;
 
 /* One queue for each sleeping process in the system. */
 struct sem_queue {
@@ -175,7 +157,7 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it);
  *	sem_array.sem_undo
  *
  * b) global or semaphore sem_lock() for read/write:
- *	sem_array.sem_base[i].pending_{const,alter}:
+ *	sem_array.sems[i].pending_{const,alter}:
  *
  * c) special:
  *	sem_undo_list.list_proc:
@@ -250,7 +232,7 @@ static void unmerge_queues(struct sem_array *sma)
 	 */
 	list_for_each_entry_safe(q, tq, &sma->pending_alter, list) {
 		struct sem *curr;
-		curr = &sma->sem_base[q->sops[0].sem_num];
+		curr = &sma->sems[q->sops[0].sem_num];
 
 		list_add_tail(&q->list, &curr->pending_alter);
 	}
@@ -270,7 +252,7 @@ static void merge_queues(struct sem_array *sma)
 {
 	int i;
 	for (i = 0; i < sma->sem_nsems; i++) {
-		struct sem *sem = sma->sem_base + i;
+		struct sem *sem = &sma->sems[i];
 
 		list_splice_init(&sem->pending_alter, &sma->pending_alter);
 	}
@@ -278,11 +260,11 @@ static void merge_queues(struct sem_array *sma)
 
 static void sem_rcu_free(struct rcu_head *head)
 {
-	struct ipc_rcu *p = container_of(head, struct ipc_rcu, rcu);
-	struct sem_array *sma = ipc_rcu_to_struct(p);
+	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);
-	ipc_rcu_free(head);
+	kvfree(sma);
 }
 
 /*
@@ -306,7 +288,7 @@ static void complexmode_enter(struct sem_array *sma)
 	sma->use_global_lock = USE_GLOBAL_LOCK_HYSTERESIS;
 
 	for (i = 0; i < sma->sem_nsems; i++) {
-		sem = sma->sem_base + i;
+		sem = &sma->sems[i];
 		spin_lock(&sem->lock);
 		spin_unlock(&sem->lock);
 	}
@@ -366,7 +348,7 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 	 *
 	 * Both facts are tracked by use_global_mode.
 	 */
-	sem = sma->sem_base + sops->sem_num;
+	sem = &sma->sems[sops->sem_num];
 
 	/*
 	 * Initial check for use_global_lock. Just an optimization,
@@ -421,7 +403,7 @@ static inline void sem_unlock(struct sem_array *sma, int locknum)
 		complexmode_tryleave(sma);
 		ipc_unlock_object(&sma->sem_perm);
 	} else {
-		struct sem *sem = sma->sem_base + locknum;
+		struct sem *sem = &sma->sems[locknum];
 		spin_unlock(&sem->lock);
 	}
 }
@@ -456,7 +438,7 @@ static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns
 static inline void sem_lock_and_putref(struct sem_array *sma)
 {
 	sem_lock(sma, NULL, -1);
-	ipc_rcu_putref(sma, sem_rcu_free);
+	ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
 }
 
 static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
@@ -464,6 +446,24 @@ 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;
+	size_t size;
+
+	if (nsems > (INT_MAX - sizeof(*sma)) / sizeof(sma->sems[0]))
+		return NULL;
+
+	size = sizeof(*sma) + nsems * sizeof(sma->sems[0]);
+	sma = kvmalloc(size, GFP_KERNEL);
+	if (unlikely(!sma))
+		return NULL;
+
+	memset(sma, 0, size);
+
+	return sma;
+}
+
 /**
  * newary - Create a new semaphore set
  * @ns: namespace
@@ -473,10 +473,8 @@ static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
  */
 static int newary(struct ipc_namespace *ns, struct ipc_params *params)
 {
-	int id;
 	int retval;
 	struct sem_array *sma;
-	int size;
 	key_t key = params->key;
 	int nsems = params->u.nsems;
 	int semflg = params->flg;
@@ -487,29 +485,24 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
 	if (ns->used_sems + nsems > ns->sc_semmns)
 		return -ENOSPC;
 
-	size = sizeof(*sma) + nsems * sizeof(struct sem);
-	sma = ipc_rcu_alloc(size);
+	sma = sem_alloc(nsems);
 	if (!sma)
 		return -ENOMEM;
 
-	memset(sma, 0, size);
-
 	sma->sem_perm.mode = (semflg & S_IRWXUGO);
 	sma->sem_perm.key = key;
 
 	sma->sem_perm.security = NULL;
 	retval = security_sem_alloc(sma);
 	if (retval) {
-		ipc_rcu_putref(sma, ipc_rcu_free);
+		kvfree(sma);
 		return retval;
 	}
 
-	sma->sem_base = (struct sem *) &sma[1];
-
 	for (i = 0; i < nsems; i++) {
-		INIT_LIST_HEAD(&sma->sem_base[i].pending_alter);
-		INIT_LIST_HEAD(&sma->sem_base[i].pending_const);
-		spin_lock_init(&sma->sem_base[i].lock);
+		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;
@@ -520,10 +513,10 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params)
 	sma->sem_nsems = nsems;
 	sma->sem_ctime = get_seconds();
 
-	id = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni);
-	if (id < 0) {
-		ipc_rcu_putref(sma, sem_rcu_free);
-		return id;
+	retval = ipc_addid(&sem_ids(ns), &sma->sem_perm, ns->sc_semmni);
+	if (retval < 0) {
+		call_rcu(&sma->sem_perm.rcu, sem_rcu_free);
+		return retval;
 	}
 	ns->used_sems += nsems;
 
@@ -612,7 +605,7 @@ static int perform_atomic_semop_slow(struct sem_array *sma, struct sem_queue *q)
 	un = q->undo;
 
 	for (sop = sops; sop < sops + nsops; sop++) {
-		curr = sma->sem_base + sop->sem_num;
+		curr = &sma->sems[sop->sem_num];
 		sem_op = sop->sem_op;
 		result = curr->semval;
 
@@ -639,7 +632,7 @@ static int perform_atomic_semop_slow(struct sem_array *sma, struct sem_queue *q)
 	sop--;
 	pid = q->pid;
 	while (sop >= sops) {
-		sma->sem_base[sop->sem_num].sempid = pid;
+		sma->sems[sop->sem_num].sempid = pid;
 		sop--;
 	}
 
@@ -661,7 +654,7 @@ undo:
 	sop--;
 	while (sop >= sops) {
 		sem_op = sop->sem_op;
-		sma->sem_base[sop->sem_num].semval -= sem_op;
+		sma->sems[sop->sem_num].semval -= sem_op;
 		if (sop->sem_flg & SEM_UNDO)
 			un->semadj[sop->sem_num] += sem_op;
 		sop--;
@@ -692,7 +685,7 @@ static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q)
 	 * until the operations can go through.
 	 */
 	for (sop = sops; sop < sops + nsops; sop++) {
-		curr = sma->sem_base + sop->sem_num;
+		curr = &sma->sems[sop->sem_num];
 		sem_op = sop->sem_op;
 		result = curr->semval;
 
@@ -716,7 +709,7 @@ static int perform_atomic_semop(struct sem_array *sma, struct sem_queue *q)
 	}
 
 	for (sop = sops; sop < sops + nsops; sop++) {
-		curr = sma->sem_base + sop->sem_num;
+		curr = &sma->sems[sop->sem_num];
 		sem_op = sop->sem_op;
 		result = curr->semval;
 
@@ -815,7 +808,7 @@ static int wake_const_ops(struct sem_array *sma, int semnum,
 	if (semnum == -1)
 		pending_list = &sma->pending_const;
 	else
-		pending_list = &sma->sem_base[semnum].pending_const;
+		pending_list = &sma->sems[semnum].pending_const;
 
 	list_for_each_entry_safe(q, tmp, pending_list, list) {
 		int error = perform_atomic_semop(sma, q);
@@ -856,7 +849,7 @@ static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
 		for (i = 0; i < nsops; i++) {
 			int num = sops[i].sem_num;
 
-			if (sma->sem_base[num].semval == 0) {
+			if (sma->sems[num].semval == 0) {
 				got_zero = 1;
 				semop_completed |= wake_const_ops(sma, num, wake_q);
 			}
@@ -867,7 +860,7 @@ static int do_smart_wakeup_zero(struct sem_array *sma, struct sembuf *sops,
 		 * Assume all were changed.
 		 */
 		for (i = 0; i < sma->sem_nsems; i++) {
-			if (sma->sem_base[i].semval == 0) {
+			if (sma->sems[i].semval == 0) {
 				got_zero = 1;
 				semop_completed |= wake_const_ops(sma, i, wake_q);
 			}
@@ -909,7 +902,7 @@ static int update_queue(struct sem_array *sma, int semnum, struct wake_q_head *w
 	if (semnum == -1)
 		pending_list = &sma->pending_alter;
 	else
-		pending_list = &sma->sem_base[semnum].pending_alter;
+		pending_list = &sma->sems[semnum].pending_alter;
 
 again:
 	list_for_each_entry_safe(q, tmp, pending_list, list) {
@@ -922,7 +915,7 @@ again:
 		 * be in the  per semaphore pending queue, and decrements
 		 * cannot be successful if the value is already 0.
 		 */
-		if (semnum != -1 && sma->sem_base[semnum].semval == 0)
+		if (semnum != -1 && sma->sems[semnum].semval == 0)
 			break;
 
 		error = perform_atomic_semop(sma, q);
@@ -959,9 +952,9 @@ again:
 static void set_semotime(struct sem_array *sma, struct sembuf *sops)
 {
 	if (sops == NULL) {
-		sma->sem_base[0].sem_otime = get_seconds();
+		sma->sems[0].sem_otime = get_seconds();
 	} else {
-		sma->sem_base[sops[0].sem_num].sem_otime =
+		sma->sems[sops[0].sem_num].sem_otime =
 							get_seconds();
 	}
 }
@@ -1067,9 +1060,9 @@ static int count_semcnt(struct sem_array *sma, ushort semnum,
 	semcnt = 0;
 	/* First: check the simple operations. They are easy to evaluate */
 	if (count_zero)
-		l = &sma->sem_base[semnum].pending_const;
+		l = &sma->sems[semnum].pending_const;
 	else
-		l = &sma->sem_base[semnum].pending_alter;
+		l = &sma->sems[semnum].pending_alter;
 
 	list_for_each_entry(q, l, list) {
 		/* all task on a per-semaphore list sleep on exactly
@@ -1124,7 +1117,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 		wake_up_sem_queue_prepare(q, -EIDRM, &wake_q);
 	}
 	for (i = 0; i < sma->sem_nsems; i++) {
-		struct sem *sem = sma->sem_base + 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);
@@ -1142,7 +1135,7 @@ static void freeary(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 
 	wake_up_q(&wake_q);
 	ns->used_sems -= sma->sem_nsems;
-	ipc_rcu_putref(sma, sem_rcu_free);
+	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)
@@ -1174,9 +1167,9 @@ static time_t get_semotime(struct sem_array *sma)
 	int i;
 	time_t res;
 
-	res = sma->sem_base[0].sem_otime;
+	res = sma->sems[0].sem_otime;
 	for (i = 1; i < sma->sem_nsems; i++) {
-		time_t to = sma->sem_base[i].sem_otime;
+		time_t to = sma->sems[i].sem_otime;
 
 		if (to > res)
 			res = to;
@@ -1325,7 +1318,7 @@ static int semctl_setval(struct ipc_namespace *ns, int semid, int semnum,
 		return -EIDRM;
 	}
 
-	curr = &sma->sem_base[semnum];
+	curr = &sma->sems[semnum];
 
 	ipc_assert_locked_object(&sma->sem_perm);
 	list_for_each_entry(un, &sma->list_id, list_id)
@@ -1382,15 +1375,16 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 			goto out_unlock;
 		}
 		if (nsems > SEMMSL_FAST) {
-			if (!ipc_rcu_getref(sma)) {
+			if (!ipc_rcu_getref(&sma->sem_perm)) {
 				err = -EIDRM;
 				goto out_unlock;
 			}
 			sem_unlock(sma, -1);
 			rcu_read_unlock();
-			sem_io = ipc_alloc(sizeof(ushort)*nsems);
+			sem_io = kvmalloc_array(nsems, sizeof(ushort),
+						GFP_KERNEL);
 			if (sem_io == NULL) {
-				ipc_rcu_putref(sma, sem_rcu_free);
+				ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
 				return -ENOMEM;
 			}
 
@@ -1402,7 +1396,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 			}
 		}
 		for (i = 0; i < sma->sem_nsems; i++)
-			sem_io[i] = sma->sem_base[i].semval;
+			sem_io[i] = sma->sems[i].semval;
 		sem_unlock(sma, -1);
 		rcu_read_unlock();
 		err = 0;
@@ -1415,29 +1409,30 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		int i;
 		struct sem_undo *un;
 
-		if (!ipc_rcu_getref(sma)) {
+		if (!ipc_rcu_getref(&sma->sem_perm)) {
 			err = -EIDRM;
 			goto out_rcu_wakeup;
 		}
 		rcu_read_unlock();
 
 		if (nsems > SEMMSL_FAST) {
-			sem_io = ipc_alloc(sizeof(ushort)*nsems);
+			sem_io = kvmalloc_array(nsems, sizeof(ushort),
+						GFP_KERNEL);
 			if (sem_io == NULL) {
-				ipc_rcu_putref(sma, sem_rcu_free);
+				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_rcu_free);
+			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_rcu_free);
+				ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
 				err = -ERANGE;
 				goto out_free;
 			}
@@ -1450,8 +1445,8 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		}
 
 		for (i = 0; i < nsems; i++) {
-			sma->sem_base[i].semval = sem_io[i];
-			sma->sem_base[i].sempid = task_tgid_vnr(current);
+			sma->sems[i].semval = sem_io[i];
+			sma->sems[i].sempid = task_tgid_vnr(current);
 		}
 
 		ipc_assert_locked_object(&sma->sem_perm);
@@ -1476,7 +1471,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
 		err = -EIDRM;
 		goto out_unlock;
 	}
-	curr = &sma->sem_base[semnum];
+	curr = &sma->sems[semnum];
 
 	switch (cmd) {
 	case GETVAL:
@@ -1500,7 +1495,7 @@ out_rcu_wakeup:
 	wake_up_q(&wake_q);
 out_free:
 	if (sem_io != fast_sem_io)
-		ipc_free(sem_io);
+		kvfree(sem_io);
 	return err;
 }
 
@@ -1719,7 +1714,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
 	}
 
 	nsems = sma->sem_nsems;
-	if (!ipc_rcu_getref(sma)) {
+	if (!ipc_rcu_getref(&sma->sem_perm)) {
 		rcu_read_unlock();
 		un = ERR_PTR(-EIDRM);
 		goto out;
@@ -1729,7 +1724,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
 	/* step 2: allocate new undo structure */
 	new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL);
 	if (!new) {
-		ipc_rcu_putref(sma, sem_rcu_free);
+		ipc_rcu_putref(&sma->sem_perm, sem_rcu_free);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -1932,7 +1927,7 @@ SYSCALL_DEFINE4(semtimedop, int, semid, struct sembuf __user *, tsops,
 	 */
 	if (nsops == 1) {
 		struct sem *curr;
-		curr = &sma->sem_base[sops->sem_num];
+		curr = &sma->sems[sops->sem_num];
 
 		if (alter) {
 			if (sma->complex_count) {
@@ -2146,7 +2141,7 @@ void exit_sem(struct task_struct *tsk)
 
 		/* perform adjustments registered in un */
 		for (i = 0; i < sma->sem_nsems; i++) {
-			struct sem *semaphore = &sma->sem_base[i];
+			struct sem *semaphore = &sma->sems[i];
 			if (un->semadj[i]) {
 				semaphore->semval += un->semadj[i];
 				/*