31 files changed, 2182 insertions, 343 deletions

diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 9fdba03dc1f..bf987b95b35 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -52,28 +52,3 @@ config PREEMPT
 
 endchoice
 
-config PREEMPT_RCU
-	bool "Preemptible RCU"
-	depends on PREEMPT
-	default n
-	help
-	  This option reduces the latency of the kernel by making certain
-	  RCU sections preemptible. Normally RCU code is non-preemptible, if
-	  this option is selected then read-only RCU sections become
-	  preemptible. This helps latency, but may expose bugs due to
-	  now-naive assumptions about each RCU read-side critical section
-	  remaining on a given CPU through its execution.
-
-	  Say N if you are unsure.
-
-config RCU_TRACE
-	bool "Enable tracing for RCU - currently stats in debugfs"
-	depends on PREEMPT_RCU
-	select DEBUG_FS
-	default y
-	help
-	  This option provides tracing in RCU which presents stats
-	  in debugfs for debugging RCU implementation.
-
-	  Say Y here if you want to enable RCU tracing
-	  Say N if you are unsure.
diff --git a/kernel/Makefile b/kernel/Makefile
index 19fad003b19..b4fdbbff5ec 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -74,10 +74,10 @@ obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
 obj-$(CONFIG_CLASSIC_RCU) += rcuclassic.o
+obj-$(CONFIG_TREE_RCU) += rcutree.o
 obj-$(CONFIG_PREEMPT_RCU) += rcupreempt.o
-ifeq ($(CONFIG_PREEMPT_RCU),y)
-obj-$(CONFIG_RCU_TRACE) += rcupreempt_trace.o
-endif
+obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o
+obj-$(CONFIG_PREEMPT_RCU_TRACE) += rcupreempt_trace.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
diff --git a/kernel/audit.c b/kernel/audit.c
index 4414e93d875..ce6d8ea3131 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -61,8 +61,11 @@
 
 #include "audit.h"
 
-/* No auditing will take place until audit_initialized != 0.
+/* No auditing will take place until audit_initialized == AUDIT_INITIALIZED.
  * (Initialization happens after skb_init is called.) */
+#define AUDIT_DISABLED		-1
+#define AUDIT_UNINITIALIZED	0
+#define AUDIT_INITIALIZED	1
 static int	audit_initialized;
 
 #define AUDIT_OFF	0
@@ -965,6 +968,9 @@ static int __init audit_init(void)
 {
 	int i;
 
+	if (audit_initialized == AUDIT_DISABLED)
+		return 0;
+
 	printk(KERN_INFO "audit: initializing netlink socket (%s)\n",
 	       audit_default ? "enabled" : "disabled");
 	audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT, 0,
@@ -976,7 +982,7 @@ static int __init audit_init(void)
 
 	skb_queue_head_init(&audit_skb_queue);
 	skb_queue_head_init(&audit_skb_hold_queue);
-	audit_initialized = 1;
+	audit_initialized = AUDIT_INITIALIZED;
 	audit_enabled = audit_default;
 	audit_ever_enabled |= !!audit_default;
 
@@ -999,13 +1005,21 @@ __initcall(audit_init);
 static int __init audit_enable(char *str)
 {
 	audit_default = !!simple_strtol(str, NULL, 0);
-	printk(KERN_INFO "audit: %s%s\n",
-	       audit_default ? "enabled" : "disabled",
-	       audit_initialized ? "" : " (after initialization)");
-	if (audit_initialized) {
+	if (!audit_default)
+		audit_initialized = AUDIT_DISABLED;
+
+	printk(KERN_INFO "audit: %s", audit_default ? "enabled" : "disabled");
+
+	if (audit_initialized == AUDIT_INITIALIZED) {
 		audit_enabled = audit_default;
 		audit_ever_enabled |= !!audit_default;
+	} else if (audit_initialized == AUDIT_UNINITIALIZED) {
+		printk(" (after initialization)");
+	} else {
+		printk(" (until reboot)");
 	}
+	printk("\n");
+
 	return 1;
 }
 
@@ -1107,9 +1121,7 @@ unsigned int audit_serial(void)
 static inline void audit_get_stamp(struct audit_context *ctx,
 				   struct timespec *t, unsigned int *serial)
 {
-	if (ctx)
-		auditsc_get_stamp(ctx, t, serial);
-	else {
+	if (!ctx || !auditsc_get_stamp(ctx, t, serial)) {
 		*t = CURRENT_TIME;
 		*serial = audit_serial();
 	}
@@ -1146,7 +1158,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 	int reserve;
 	unsigned long timeout_start = jiffies;
 
-	if (!audit_initialized)
+	if (audit_initialized != AUDIT_INITIALIZED)
 		return NULL;
 
 	if (unlikely(audit_filter_type(type)))
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index cf5bc2f5f9c..2a3f0afc4d2 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1459,7 +1459,6 @@ void audit_free(struct task_struct *tsk)
 
 /**
  * audit_syscall_entry - fill in an audit record at syscall entry
- * @tsk: task being audited
  * @arch: architecture type
  * @major: major syscall type (function)
  * @a1: additional syscall register 1
@@ -1548,9 +1547,25 @@ void audit_syscall_entry(int arch, int major,
 	context->ppid       = 0;
 }
 
+void audit_finish_fork(struct task_struct *child)
+{
+	struct audit_context *ctx = current->audit_context;
+	struct audit_context *p = child->audit_context;
+	if (!p || !ctx || !ctx->auditable)
+		return;
+	p->arch = ctx->arch;
+	p->major = ctx->major;
+	memcpy(p->argv, ctx->argv, sizeof(ctx->argv));
+	p->ctime = ctx->ctime;
+	p->dummy = ctx->dummy;
+	p->auditable = ctx->auditable;
+	p->in_syscall = ctx->in_syscall;
+	p->filterkey = kstrdup(ctx->filterkey, GFP_KERNEL);
+	p->ppid = current->pid;
+}
+
 /**
  * audit_syscall_exit - deallocate audit context after a system call
- * @tsk: task being audited
  * @valid: success/failure flag
  * @return_code: syscall return value
  *
@@ -1942,15 +1957,18 @@ EXPORT_SYMBOL_GPL(__audit_inode_child);
  *
  * Also sets the context as auditable.
  */
-void auditsc_get_stamp(struct audit_context *ctx,
+int auditsc_get_stamp(struct audit_context *ctx,
 		       struct timespec *t, unsigned int *serial)
 {
+	if (!ctx->in_syscall)
+		return 0;
 	if (!ctx->serial)
 		ctx->serial = audit_serial();
 	t->tv_sec  = ctx->ctime.tv_sec;
 	t->tv_nsec = ctx->ctime.tv_nsec;
 	*serial    = ctx->serial;
 	ctx->auditable = 1;
+	return 1;
 }
 
 /* global counter which is incremented every time something logs in */
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index fe00b3b983a..2606d0fb4e5 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -702,7 +702,7 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 	 * any child cgroups exist. This is theoretically supportable
 	 * but involves complex error handling, so it's being left until
 	 * later */
-	if (!list_empty(&cgrp->children))
+	if (root->number_of_cgroups > 1)
 		return -EBUSY;
 
 	/* Process each subsystem */
@@ -1024,7 +1024,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 		if (ret == -EBUSY) {
 			mutex_unlock(&cgroup_mutex);
 			mutex_unlock(&inode->i_mutex);
-			goto drop_new_super;
+			goto free_cg_links;
 		}
 
 		/* EBUSY should be the only error here */
@@ -1073,10 +1073,11 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 
 	return simple_set_mnt(mnt, sb);
 
+ free_cg_links:
+	free_cg_links(&tmp_cg_links);
  drop_new_super:
 	up_write(&sb->s_umount);
 	deactivate_super(sb);
-	free_cg_links(&tmp_cg_links);
 	return ret;
 }
 
@@ -2934,9 +2935,6 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
  again:
 	root = subsys->root;
 	if (root == &rootnode) {
-		printk(KERN_INFO
-		       "Not cloning cgroup for unused subsystem %s\n",
-		       subsys->name);
 		mutex_unlock(&cgroup_mutex);
 		return 0;
 	}
diff --git a/kernel/exit.c b/kernel/exit.c
index 2d8be7ebb0f..30fcdf16737 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1321,10 +1321,10 @@ static int wait_task_zombie(struct task_struct *p, int options,
 		 * group, which consolidates times for all threads in the
 		 * group including the group leader.
 		 */
+		thread_group_cputime(p, &cputime);
 		spin_lock_irq(&p->parent->sighand->siglock);
 		psig = p->parent->signal;
 		sig = p->signal;
-		thread_group_cputime(p, &cputime);
 		psig->cutime =
 			cputime_add(psig->cutime,
 			cputime_add(cputime.utime,
diff --git a/kernel/extable.c b/kernel/extable.c
index a26cb2e1702..adf0cc9c02d 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -66,3 +66,19 @@ int kernel_text_address(unsigned long addr)
 		return 1;
 	return module_text_address(addr) != NULL;
 }
+
+/*
+ * On some architectures (PPC64, IA64) function pointers
+ * are actually only tokens to some data that then holds the
+ * real function address. As a result, to find if a function
+ * pointer is part of the kernel text, we need to do some
+ * special dereferencing first.
+ */
+int func_ptr_is_kernel_text(void *ptr)
+{
+	unsigned long addr;
+	addr = (unsigned long) dereference_function_descriptor(ptr);
+	if (core_kernel_text(addr))
+		return 1;
+	return module_text_address(addr) != NULL;
+}
diff --git a/kernel/fork.c b/kernel/fork.c
index 2a372a0e206..495da2e9a8b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -315,17 +315,20 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		file = tmp->vm_file;
 		if (file) {
 			struct inode *inode = file->f_path.dentry->d_inode;
+			struct address_space *mapping = file->f_mapping;
+
 			get_file(file);
 			if (tmp->vm_flags & VM_DENYWRITE)
 				atomic_dec(&inode->i_writecount);
-
-			/* insert tmp into the share list, just after mpnt */
-			spin_lock(&file->f_mapping->i_mmap_lock);
+			spin_lock(&mapping->i_mmap_lock);
+			if (tmp->vm_flags & VM_SHARED)
+				mapping->i_mmap_writable++;
 			tmp->vm_truncate_count = mpnt->vm_truncate_count;
-			flush_dcache_mmap_lock(file->f_mapping);
+			flush_dcache_mmap_lock(mapping);
+			/* insert tmp into the share list, just after mpnt */
 			vma_prio_tree_add(tmp, mpnt);
-			flush_dcache_mmap_unlock(file->f_mapping);
-			spin_unlock(&file->f_mapping->i_mmap_lock);
+			flush_dcache_mmap_unlock(mapping);
+			spin_unlock(&mapping->i_mmap_lock);
 		}
 
 		/*
@@ -1398,6 +1401,7 @@ long do_fork(unsigned long clone_flags,
 			init_completion(&vfork);
 		}
 
+		audit_finish_fork(p);
 		tracehook_report_clone(trace, regs, clone_flags, nr, p);
 
 		/*
diff --git a/kernel/futex.c b/kernel/futex.c
index 8af10027514..b4f87bac91c 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -92,11 +92,12 @@ struct futex_pi_state {
  * A futex_q has a woken state, just like tasks have TASK_RUNNING.
  * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0.
  * The order of wakup is always to make the first condition true, then
- * wake up q->waiters, then make the second condition true.
+ * wake up q->waiter, then make the second condition true.
  */
 struct futex_q {
 	struct plist_node list;
-	wait_queue_head_t waiters;
+	/* There can only be a single waiter */
+	wait_queue_head_t waiter;
 
 	/* Which hash list lock to use: */
 	spinlock_t *lock_ptr;
@@ -123,24 +124,6 @@ struct futex_hash_bucket {
 static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS];
 
 /*
- * Take mm->mmap_sem, when futex is shared
- */
-static inline void futex_lock_mm(struct rw_semaphore *fshared)
-{
-	if (fshared)
-		down_read(fshared);
-}
-
-/*
- * Release mm->mmap_sem, when the futex is shared
- */
-static inline void futex_unlock_mm(struct rw_semaphore *fshared)
-{
-	if (fshared)
-		up_read(fshared);
-}
-
-/*
  * We hash on the keys returned from get_futex_key (see below).
  */
 static struct futex_hash_bucket *hash_futex(union futex_key *key)
@@ -161,6 +144,45 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2)
 		&& key1->both.offset == key2->both.offset);
 }
 
+/*
+ * Take a reference to the resource addressed by a key.
+ * Can be called while holding spinlocks.
+ *
+ */
+static void get_futex_key_refs(union futex_key *key)
+{
+	if (!key->both.ptr)
+		return;
+
+	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
+	case FUT_OFF_INODE:
+		atomic_inc(&key->shared.inode->i_count);
+		break;
+	case FUT_OFF_MMSHARED:
+		atomic_inc(&key->private.mm->mm_count);
+		break;
+	}
+}
+
+/*
+ * Drop a reference to the resource addressed by a key.
+ * The hash bucket spinlock must not be held.
+ */
+static void drop_futex_key_refs(union futex_key *key)
+{
+	if (!key->both.ptr)
+		return;
+
+	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
+	case FUT_OFF_INODE:
+		iput(key->shared.inode);
+		break;
+	case FUT_OFF_MMSHARED:
+		mmdrop(key->private.mm);
+		break;
+	}
+}
+
 /**
  * get_futex_key - Get parameters which are the keys for a futex.
  * @uaddr: virtual address of the futex
@@ -179,12 +201,10 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2)
  * For other futexes, it points to &current->mm->mmap_sem and
  * caller must have taken the reader lock. but NOT any spinlocks.
  */
-static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared,
-			 union futex_key *key)
+static int get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key)
 {
 	unsigned long address = (unsigned long)uaddr;
 	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
 	struct page *page;
 	int err;
 
@@ -208,100 +228,50 @@ static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared,
 			return -EFAULT;
 		key->private.mm = mm;
 		key->private.address = address;
+		get_futex_key_refs(key);
 		return 0;
 	}
-	/*
-	 * The futex is hashed differently depending on whether
-	 * it's in a shared or private mapping.  So check vma first.
-	 */
-	vma = find_extend_vma(mm, address);
-	if (unlikely(!vma))
-		return -EFAULT;
 
-	/*
-	 * Permissions.
-	 */
-	if (unlikely((vma->vm_flags & (VM_IO|VM_READ)) != VM_READ))
-		return (vma->vm_flags & VM_IO) ? -EPERM : -EACCES;
+again:
+	err = get_user_pages_fast(address, 1, 0, &page);
+	if (err < 0)
+		return err;
+
+	lock_page(page);
+	if (!page->mapping) {
+		unlock_page(page);
+		put_page(page);
+		goto again;
+	}
 
 	/*
 	 * Private mappings are handled in a simple way.
 	 *
 	 * NOTE: When userspace waits on a MAP_SHARED mapping, even if
 	 * it's a read-only handle, it's expected that futexes attach to
-	 * the object not the particular process.  Therefore we use
-	 * VM_MAYSHARE here, not VM_SHARED which is restricted to shared
-	 * mappings of _writable_ handles.
+	 * the object not the particular process.
 	 */
-	if (likely(!(vma->vm_flags & VM_MAYSHARE))) {
-		key->both.offset |= FUT_OFF_MMSHARED; /* reference taken on mm */
+	if (PageAnon(page)) {
+		key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
 		key->private.mm = mm;
 		key->private.address = address;
-		return 0;
+	} else {
+		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
+		key->shared.inode = page->mapping->host;
+		key->shared.pgoff = page->index;
 	}
 
-	/*
-	 * Linear file mappings are also simple.
-	 */
-	key->shared.inode = vma->vm_file->f_path.dentry->d_inode;
-	key->both.offset |= FUT_OFF_INODE; /* inode-based key. */
-	if (likely(!(vma->vm_flags & VM_NONLINEAR))) {
-		key->shared.pgoff = (((address - vma->vm_start) >> PAGE_SHIFT)
-				     + vma->vm_pgoff);
-		return 0;
-	}
+	get_futex_key_refs(key);
 
-	/*
-	 * We could walk the page table to read the non-linear
-	 * pte, and get the page index without fetching the page
-	 * from swap.  But that's a lot of code to duplicate here
-	 * for a rare case, so we simply fetch the page.
-	 */
-	err = get_user_pages(current, mm, address, 1, 0, 0, &page, NULL);
-	if (err >= 0) {
-		key->shared.pgoff =
-			page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-		put_page(page);
-		return 0;
-	}
-	return err;
-}
-
-/*
- * Take a reference to the resource addressed by a key.
- * Can be called while holding spinlocks.
- *
- */
-static void get_futex_key_refs(union futex_key *key)
-{
-	if (key->both.ptr == NULL)
-		return;
-	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
-		case FUT_OFF_INODE:
-			atomic_inc(&key->shared.inode->i_count);
-			break;
-		case FUT_OFF_MMSHARED:
-			atomic_inc(&key->private.mm->mm_count);
-			break;
-	}
+	unlock_page(page);
+	put_page(page);
+	return 0;
 }
 
-/*
- * Drop a reference to the resource addressed by a key.
- * The hash bucket spinlock must not be held.
- */
-static void drop_futex_key_refs(union futex_key *key)
+static inline
+void put_futex_key(int fshared, union futex_key *key)
 {
-	if (!key->both.ptr)
-		return;
-	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
-		case FUT_OFF_INODE:
-			iput(key->shared.inode);
-			break;
-		case FUT_OFF_MMSHARED:
-			mmdrop(key->private.mm);
-			break;
-	}
+	drop_futex_key_refs(key);
 }
 
 static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
@@ -328,10 +298,8 @@ static int get_futex_value_locked(u32 *dest, u32 __user *from)
 
 /*
  * Fault handling.
- * if fshared is non NULL, current->mm->mmap_sem is already held
  */
-static int futex_handle_fault(unsigned long address,
-			      struct rw_semaphore *fshared, int attempt)
+static int futex_handle_fault(unsigned long address, int attempt)
 {
 	struct vm_area_struct * vma;
 	struct mm_struct *mm = current->mm;
@@ -340,8 +308,7 @@ static int futex_handle_fault(unsigned long address,
 	if (attempt > 2)
 		return ret;
 
-	if (!fshared)
-		down_read(&mm->mmap_sem);
+	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
 	if (vma && address >= vma->vm_start &&
 	    (vma->vm_flags & VM_WRITE)) {
@@ -361,8 +328,7 @@ static int futex_handle_fault(unsigned long address,
 				current->min_flt++;
 		}
 	}
-	if (!fshared)
-		up_read(&mm->mmap_sem);
+	up_read(&mm->mmap_sem);
 	return ret;
 }
 
@@ -385,6 +351,7 @@ static int refill_pi_state_cache(void)
 	/* pi_mutex gets initialized later */
 	pi_state->owner = NULL;
 	atomic_set(&pi_state->refcount, 1);
+	pi_state->key = FUTEX_KEY_INIT;
 
 	current->pi_state_cache = pi_state;
 
@@ -462,7 +429,7 @@ void exit_pi_state_list(struct task_struct *curr)
 	struct list_head *next, *head = &curr->pi_state_list;
 	struct futex_pi_state *pi_state;
 	struct futex_hash_bucket *hb;
-	union futex_key key;
+	union futex_key key = FUTEX_KEY_INIT;
 
 	if (!futex_cmpxchg_enabled)
 		return;
@@ -607,7 +574,7 @@ static void wake_futex(struct futex_q *q)
 	 * The lock in wake_up_all() is a crucial memory barrier after the
 	 * plist_del() and also before assigning to q->lock_ptr.
 	 */
-	wake_up_all(&q->waiters);
+	wake_up(&q->waiter);
 	/*
 	 * The waiting task can free the futex_q as soon as this is written,
 	 * without taking any locks.  This must come last.
@@ -719,20 +686,17 @@ double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
  * Wake up all waiters hashed on the physical page that is mapped
  * to this virtual address:
  */
-static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared,
-		      int nr_wake, u32 bitset)
+static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
 	struct plist_head *head;
-	union futex_key key;
+	union futex_key key = FUTEX_KEY_INIT;
 	int ret;
 
 	if (!bitset)
 		return -EINVAL;
 
-	futex_lock_mm(fshared);
-
 	ret = get_futex_key(uaddr, fshared, &key);
 	if (unlikely(ret != 0))
 		goto out;
@@ -760,7 +724,7 @@ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared,
 
 	spin_unlock(&hb->lock);
 out:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &key);
 	return ret;
 }
 
@@ -769,19 +733,16 @@ out:
  * to this virtual address:
  */
 static int
-futex_wake_op(u32 __user *uaddr1, struct rw_semaphore *fshared,
-	      u32 __user *uaddr2,
+futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
 	      int nr_wake, int nr_wake2, int op)
 {
-	union futex_key key1, key2;
+	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct plist_head *head;
 	struct futex_q *this, *next;
 	int ret, op_ret, attempt = 0;
 
 retryfull:
-	futex_lock_mm(fshared);
-
 	ret = get_futex_key(uaddr1, fshared, &key1);
 	if (unlikely(ret != 0))
 		goto out;
@@ -826,18 +787,12 @@ retry:
 		 */
 		if (attempt++) {
 			ret = futex_handle_fault((unsigned long)uaddr2,
-						 fshared, attempt);
+						 attempt);
 			if (ret)
 				goto out;
 			goto retry;
 		}
 
-		/*
-		 * If we would have faulted, release mmap_sem,
-		 * fault it in and start all over again.
-		 */
-		futex_unlock_mm(fshared);
-
 		ret = get_user(dummy, uaddr2);
 		if (ret)
 			return ret;
@@ -873,7 +828,8 @@ retry:
 	if (hb1 != hb2)
 		spin_unlock(&hb2->lock);
 out:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &key2);
+	put_futex_key(fshared, &key1);
 
 	return ret;
 }
@@ -882,19 +838,16 @@ out:
  * Requeue all waiters hashed on one physical page to another
  * physical page.
  */
-static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared,
-			 u32 __user *uaddr2,
+static int futex_requeue(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
 			 int nr_wake, int nr_requeue, u32 *cmpval)
 {
-	union futex_key key1, key2;
+	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct plist_head *head1;
 	struct futex_q *this, *next;
 	int ret, drop_count = 0;
 
  retry:
-	futex_lock_mm(fshared);
-
 	ret = get_futex_key(uaddr1, fshared, &key1);
 	if (unlikely(ret != 0))
 		goto out;
@@ -917,12 +870,6 @@ static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared,
 			if (hb1 != hb2)
 				spin_unlock(&hb2->lock);
 
-			/*
-			 * If we would have faulted, release mmap_sem, fault
-			 * it in and start all over again.
-			 */
-			futex_unlock_mm(fshared);
-
 			ret = get_user(curval, uaddr1);
 
 			if (!ret)
@@ -974,7 +921,8 @@ out_unlock:
 		drop_futex_key_refs(&key1);
 
 out:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &key2);
+	put_futex_key(fshared, &key1);
 	return ret;
 }
 
@@ -983,7 +931,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 {
 	struct futex_hash_bucket *hb;
 
-	init_waitqueue_head(&q->waiters);
+	init_waitqueue_head(&q->waiter);
 
 	get_futex_key_refs(&q->key);
 	hb = hash_futex(&q->key);
@@ -1096,8 +1044,7 @@ static void unqueue_me_pi(struct futex_q *q)
  * private futexes.
  */
 static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
-				struct task_struct *newowner,
-				struct rw_semaphore *fshared)
+				struct task_struct *newowner, int fshared)
 {
 	u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
 	struct futex_pi_state *pi_state = q->pi_state;
@@ -1176,7 +1123,7 @@ retry:
 handle_fault:
 	spin_unlock(q->lock_ptr);
 
-	ret = futex_handle_fault((unsigned long)uaddr, fshared, attempt++);
+	ret = futex_handle_fault((unsigned long)uaddr, attempt++);
 
 	spin_lock(q->lock_ptr);
 
@@ -1196,12 +1143,13 @@ handle_fault:
  * In case we must use restart_block to restart a futex_wait,
  * we encode in the 'flags' shared capability
  */
-#define FLAGS_SHARED  1
+#define FLAGS_SHARED		0x01
+#define FLAGS_CLOCKRT		0x02
 
 static long futex_wait_restart(struct restart_block *restart);
 
-static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
-		      u32 val, ktime_t *abs_time, u32 bitset)
+static int futex_wait(u32 __user *uaddr, int fshared,
+		      u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
 {
 	struct task_struct *curr = current;
 	DECLARE_WAITQUEUE(wait, curr);
@@ -1218,8 +1166,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 	q.pi_state = NULL;
 	q.bitset = bitset;
  retry:
-	futex_lock_mm(fshared);
-
+	q.key = FUTEX_KEY_INIT;
 	ret = get_futex_key(uaddr, fshared, &q.key);
 	if (unlikely(ret != 0))
 		goto out_release_sem;
@@ -1251,12 +1198,6 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 	if (unlikely(ret)) {
 		queue_unlock(&q, hb);
 
-		/*
-		 * If we would have faulted, release mmap_sem, fault it in and
-		 * start all over again.
-		 */
-		futex_unlock_mm(fshared);
-
 		ret = get_user(uval, uaddr);
 
 		if (!ret)
@@ -1271,12 +1212,6 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 	queue_me(&q, hb);
 
 	/*
-	 * Now the futex is queued and we have checked the data, we
-	 * don't want to hold mmap_sem while we sleep.
-	 */
-	futex_unlock_mm(fshared);
-
-	/*
 	 * There might have been scheduling since the queue_me(), as we
 	 * cannot hold a spinlock across the get_user() in case it
 	 * faults, and we cannot just set TASK_INTERRUPTIBLE state when
@@ -1287,7 +1222,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 
 	/* add_wait_queue is the barrier after __set_current_state. */
 	__set_current_state(TASK_INTERRUPTIBLE);
-	add_wait_queue(&q.waiters, &wait);
+	add_wait_queue(&q.waiter, &wait);
 	/*
 	 * !plist_node_empty() is safe here without any lock.
 	 * q.lock_ptr != 0 is not safe, because of ordering against wakeup.
@@ -1300,8 +1235,10 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 			slack = current->timer_slack_ns;
 			if (rt_task(current))
 				slack = 0;
-			hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC,
-						HRTIMER_MODE_ABS);
+			hrtimer_init_on_stack(&t.timer,
+					      clockrt ? CLOCK_REALTIME :
+					      CLOCK_MONOTONIC,
+					      HRTIMER_MODE_ABS);
 			hrtimer_init_sleeper(&t, current);
 			hrtimer_set_expires_range_ns(&t.timer, *abs_time, slack);
 
@@ -1356,6 +1293,8 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 
 		if (fshared)
 			restart->futex.flags |= FLAGS_SHARED;
+		if (clockrt)
+			restart->futex.flags |= FLAGS_CLOCKRT;
 		return -ERESTART_RESTARTBLOCK;
 	}
 
@@ -1363,7 +1302,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 	queue_unlock(&q, hb);
 
  out_release_sem:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &q.key);