Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:

 - a couple of hotfixes

 - almost all of the rest of MM

 - lib/ updates

 - binfmt_elf updates

 - autofs updates

 - quite a lot of misc fixes and updates
    - reiserfs, fatfs
    - signals
    - exec
    - cpumask
    - rapidio
    - sysctl
    - pids
    - eventfd
    - gcov
    - panic
    - pps

 - gdb script updates

 - ipc updates

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (126 commits)
  mm: memcontrol: fix NUMA round-robin reclaim at intermediate level
  mm: memcontrol: fix recursive statistics correctness & scalabilty
  mm: memcontrol: move stat/event counting functions out-of-line
  mm: memcontrol: make cgroup stats and events query API explicitly local
  drivers/virt/fsl_hypervisor.c: prevent integer overflow in ioctl
  drivers/virt/fsl_hypervisor.c: dereferencing error pointers in ioctl
  mm, memcg: rename ambiguously named memory.stat counters and functions
  arch: remove <asm/sizes.h> and <asm-generic/sizes.h>
  treewide: replace #include <asm/sizes.h> with #include <linux/sizes.h>
  fs/block_dev.c: Remove duplicate header
  fs/cachefiles/namei.c: remove duplicate header
  include/linux/sched/signal.h: replace `tsk' with `task'
  fs/coda/psdev.c: remove duplicate header
  ipc: do cyclic id allocation for the ipc object.
  ipc: conserve sequence numbers in ipcmni_extend mode
  ipc: allow boot time extension of IPCMNI from 32k to 16M
  ipc/mqueue: optimize msg_get()
  ipc/mqueue: remove redundant wq task assignment
  ipc: prevent lockup on alloc_msg and free_msg
  scripts/gdb: print cached rate in lx-clk-summary
  ...

5 files changed, 139 insertions, 48 deletions

diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index 49f9bf4ffc7f..bfaae457810c 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -120,7 +120,9 @@ static int proc_ipc_sem_dointvec(struct ctl_table *table, int write,
 static int zero;
 static int one = 1;
 static int int_max = INT_MAX;
-static int ipc_mni = IPCMNI;
+int ipc_mni = IPCMNI;
+int ipc_mni_shift = IPCMNI_SHIFT;
+int ipc_min_cycle = RADIX_TREE_MAP_SIZE;
 
 static struct ctl_table ipc_kern_table[] = {
 	{
@@ -246,3 +248,13 @@ static int __init ipc_sysctl_init(void)
 }
 
 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/mqueue.c b/ipc/mqueue.c
index ba44164ea1f9..216cad1ff0d0 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -76,6 +76,7 @@ struct mqueue_inode_info {
 	wait_queue_head_t wait_q;
 
 	struct rb_root msg_tree;
+	struct rb_node *msg_tree_rightmost;
 	struct posix_msg_tree_node *node_cache;
 	struct mq_attr attr;
 
@@ -131,6 +132,7 @@ static int msg_insert(struct msg_msg *msg, struct mqueue_inode_info *info)
 {
 	struct rb_node **p, *parent = NULL;
 	struct posix_msg_tree_node *leaf;
+	bool rightmost = true;
 
 	p = &info->msg_tree.rb_node;
 	while (*p) {
@@ -139,9 +141,10 @@ static int msg_insert(struct msg_msg *msg, struct mqueue_inode_info *info)
 
 		if (likely(leaf->priority == msg->m_type))
 			goto insert_msg;
-		else if (msg->m_type < leaf->priority)
+		else if (msg->m_type < leaf->priority) {
 			p = &(*p)->rb_left;
-		else
+			rightmost = false;
+		} else
 			p = &(*p)->rb_right;
 	}
 	if (info->node_cache) {
@@ -154,6 +157,10 @@ static int msg_insert(struct msg_msg *msg, struct mqueue_inode_info *info)
 		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:
@@ -163,23 +170,35 @@ insert_msg:
 	return 0;
 }
 
+static inline void msg_tree_erase(struct posix_msg_tree_node *leaf,
+				  struct mqueue_inode_info *info)
+{
+	struct rb_node *node = &leaf->rb_node;
+
+	if (info->msg_tree_rightmost == node)
+		info->msg_tree_rightmost = rb_prev(node);
+
+	rb_erase(node, &info->msg_tree);
+	if (info->node_cache) {
+		kfree(leaf);
+	} else {
+		info->node_cache = leaf;
+	}
+}
+
 static inline struct msg_msg *msg_get(struct mqueue_inode_info *info)
 {
-	struct rb_node **p, *parent = NULL;
+	struct rb_node *parent = NULL;
 	struct posix_msg_tree_node *leaf;
 	struct msg_msg *msg;
 
 try_again:
-	p = &info->msg_tree.rb_node;
-	while (*p) {
-		parent = *p;
-		/*
-		 * During insert, low priorities go to the left and high to the
-		 * right.  On receive, we want the highest priorities first, so
-		 * walk all the way to the right.
-		 */
-		p = &(*p)->rb_right;
-	}
+	/*
+	 * During insert, low priorities go to the left and high to the
+	 * right.  On receive, we want the highest priorities first, so
+	 * walk all the way to the right.
+	 */
+	parent = info->msg_tree_rightmost;
 	if (!parent) {
 		if (info->attr.mq_curmsgs) {
 			pr_warn_once("Inconsistency in POSIX message queue, "
@@ -194,24 +213,14 @@ try_again:
 		pr_warn_once("Inconsistency in POSIX message queue, "
 			     "empty leaf node but we haven't implemented "
 			     "lazy leaf delete!\n");
-		rb_erase(&leaf->rb_node, &info->msg_tree);
-		if (info->node_cache) {
-			kfree(leaf);
-		} else {
-			info->node_cache = leaf;
-		}
+		msg_tree_erase(leaf, info);
 		goto try_again;
 	} else {
 		msg = list_first_entry(&leaf->msg_list,
 				       struct msg_msg, m_list);
 		list_del(&msg->m_list);
 		if (list_empty(&leaf->msg_list)) {
-			rb_erase(&leaf->rb_node, &info->msg_tree);
-			if (info->node_cache) {
-				kfree(leaf);
-			} else {
-				info->node_cache = leaf;
-			}
+			msg_tree_erase(leaf, info);
 		}
 	}
 	info->attr.mq_curmsgs--;
@@ -254,6 +263,7 @@ static struct inode *mqueue_get_inode(struct super_block *sb,
 		info->qsize = 0;
 		info->user = 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,
@@ -430,7 +440,8 @@ static void mqueue_evict_inode(struct inode *inode)
 	struct user_struct *user;
 	unsigned long mq_bytes, mq_treesize;
 	struct ipc_namespace *ipc_ns;
-	struct msg_msg *msg;
+	struct msg_msg *msg, *nmsg;
+	LIST_HEAD(tmp_msg);
 
 	clear_inode(inode);
 
@@ -441,10 +452,15 @@ static void mqueue_evict_inode(struct inode *inode)
 	info = MQUEUE_I(inode);
 	spin_lock(&info->lock);
 	while ((msg = msg_get(info)) != NULL)
-		free_msg(msg);
+		list_add_tail(&msg->m_list, &tmp_msg);
 	kfree(info->node_cache);
 	spin_unlock(&info->lock);
 
+	list_for_each_entry_safe(msg, nmsg, &tmp_msg, m_list) {
+		list_del(&msg->m_list);
+		free_msg(msg);
+	}
+
 	/* 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) *
@@ -605,8 +621,6 @@ static void wq_add(struct mqueue_inode_info *info, int sr,
 {
 	struct ext_wait_queue *walk;
 
-	ewp->task = current;
-
 	list_for_each_entry(walk, &info->e_wait_q[sr].list, list) {
 		if (walk->task->prio <= current->prio) {
 			list_add_tail(&ewp->list, &walk->list);
diff --git a/ipc/msgutil.c b/ipc/msgutil.c
index 84598025a6ad..e65593742e2b 100644
--- a/ipc/msgutil.c
+++ b/ipc/msgutil.c
@@ -18,6 +18,7 @@
 #include <linux/utsname.h>
 #include <linux/proc_ns.h>
 #include <linux/uaccess.h>
+#include <linux/sched.h>
 
 #include "util.h"
 
@@ -64,6 +65,9 @@ static struct msg_msg *alloc_msg(size_t len)
 	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)
@@ -176,6 +180,8 @@ void free_msg(struct msg_msg *msg)
 	kfree(msg);
 	while (seg != NULL) {
 		struct msg_msgseg *tmp = seg->next;
+
+		cond_resched();
 		kfree(seg);
 		seg = tmp;
 	}
diff --git a/ipc/util.c b/ipc/util.c
index 095274a871f8..d126d156efc6 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -109,7 +109,7 @@ static const struct rhashtable_params ipc_kht_params = {
  * @ids: ipc identifier set
  *
  * Set up the sequence range to use for the ipc identifier range (limited
- * below IPCMNI) then initialise the keys hashtable and ids idr.
+ * below ipc_mni) then initialise the keys hashtable and ids idr.
  */
 void ipc_init_ids(struct ipc_ids *ids)
 {
@@ -119,6 +119,7 @@ void ipc_init_ids(struct ipc_ids *ids)
 	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
@@ -192,6 +193,10 @@ static struct kern_ipc_perm *ipc_findkey(struct ipc_ids *ids, key_t key)
  *
  * 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)
 {
@@ -215,17 +220,42 @@ static inline int ipc_idr_alloc(struct ipc_ids *ids, struct kern_ipc_perm *new)
 	 */
 
 	if (next_id < 0) { /* !CHECKPOINT_RESTORE or next_id is unset */
-		new->seq = ids->seq++;
-		if (ids->seq > IPCID_SEQ_MAX)
-			ids->seq = 0;
-		idx = idr_alloc(&ids->ipcs_idr, new, 0, 0, GFP_NOWAIT);
+		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 = SEQ_MULTIPLIER * new->seq + idx;
+		new->id = (new->seq << ipcmni_seq_shift()) + idx;
 	return idx;
 }
 
@@ -253,8 +283,8 @@ int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int limit)
 	/* 1) Initialize the refcount so that ipc_rcu_putref works */
 	refcount_set(&new->refcount, 1);
 
-	if (limit > IPCMNI)
-		limit = IPCMNI;
+	if (limit > ipc_mni)
+		limit = ipc_mni;
 
 	if (ids->in_use >= limit)
 		return -ENOSPC;
@@ -737,7 +767,7 @@ static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos,
 	if (total >= ids->in_use)
 		return NULL;
 
-	for (; pos < IPCMNI; pos++) {
+	for (; pos < ipc_mni; pos++) {
 		ipc = idr_find(&ids->ipcs_idr, pos);
 		if (ipc != NULL) {
 			*new_pos = pos + 1;
diff --git a/ipc/util.h b/ipc/util.h
index e272be622ae7..0fcf8e719b76 100644
--- a/ipc/util.h
+++ b/ipc/util.h
@@ -15,8 +15,37 @@
 #include <linux/err.h>
 #include <linux/ipc_namespace.h>
 
-#define IPCMNI 32768  /* <= MAX_INT limit for ipc arrays (including sysctl changes) */
-#define SEQ_MULTIPLIER	(IPCMNI)
+/*
+ * 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);
@@ -96,9 +125,9 @@ struct pid_namespace *ipc_seq_pid_ns(struct seq_file *);
 #define IPC_MSG_IDS	1
 #define IPC_SHM_IDS	2
 
-#define ipcid_to_idx(id) ((id) % SEQ_MULTIPLIER)
-#define ipcid_to_seqx(id) ((id) / SEQ_MULTIPLIER)
-#define IPCID_SEQ_MAX min_t(int, INT_MAX/SEQ_MULTIPLIER, USHRT_MAX)
+#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);
@@ -123,8 +152,8 @@ static inline int ipc_get_maxidx(struct ipc_ids *ids)
 	if (ids->in_use == 0)
 		return -1;
 
-	if (ids->in_use == IPCMNI)
-		return IPCMNI - 1;
+	if (ids->in_use == ipc_mni)
+		return ipc_mni - 1;
 
 	return ids->max_idx;
 }
@@ -216,10 +245,10 @@ void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
 
 static inline int sem_check_semmni(struct ipc_namespace *ns) {
 	/*
-	 * Check semmni range [0, IPCMNI]
+	 * 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] > IPCMNI))
+	return ((ns->sem_ctls[3] < 0) || (ns->sem_ctls[3] > ipc_mni))
 		? -ERANGE : 0;
 }