Merge ../torvalds-2.6/

12 files changed, 442 insertions, 190 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 8d57a2f1226..ff4dc02ce17 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -12,6 +12,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
 obj-$(CONFIG_FUTEX) += futex.o
 obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
 obj-$(CONFIG_SMP) += cpu.o spinlock.o
+obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_UID16) += uid16.o
 obj-$(CONFIG_MODULES) += module.o
 obj-$(CONFIG_KALLSYMS) += kallsyms.o
diff --git a/kernel/acct.c b/kernel/acct.c
index f70e6027cca..b756f527497 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -165,7 +165,7 @@ out:
 }
 
 /*
- * Close the old accouting file (if currently open) and then replace
+ * Close the old accounting file (if currently open) and then replace
  * it with file (if non-NULL).
  *
  * NOTE: acct_globals.lock MUST be held on entry and exit.
@@ -199,11 +199,16 @@ static void acct_file_reopen(struct file *file)
 	}
 }
 
-/*
- *  sys_acct() is the only system call needed to implement process
- *  accounting. It takes the name of the file where accounting records
- *  should be written. If the filename is NULL, accounting will be
- *  shutdown.
+/**
+ * sys_acct - enable/disable process accounting
+ * @name: file name for accounting records or NULL to shutdown accounting
+ *
+ * Returns 0 for success or negative errno values for failure.
+ *
+ * sys_acct() is the only system call needed to implement process
+ * accounting. It takes the name of the file where accounting records
+ * should be written. If the filename is NULL, accounting will be
+ * shutdown.
  */
 asmlinkage long sys_acct(const char __user *name)
 {
@@ -250,9 +255,12 @@ asmlinkage long sys_acct(const char __user *name)
 	return (0);
 }
 
-/*
- * If the accouting is turned on for a file in the filesystem pointed
- * to by sb, turn accouting off.
+/**
+ * acct_auto_close - turn off a filesystem's accounting if it is on
+ * @sb: super block for the filesystem
+ *
+ * If the accounting is turned on for a file in the filesystem pointed
+ * to by sb, turn accounting off.
  */
 void acct_auto_close(struct super_block *sb)
 {
@@ -503,8 +511,11 @@ static void do_acct_process(long exitcode, struct file *file)
 	set_fs(fs);
 }
 
-/*
+/**
  * acct_process - now just a wrapper around do_acct_process
+ * @exitcode: task exit code
+ *
+ * handles process accounting for an exiting task
  */
 void acct_process(long exitcode)
 {
@@ -530,9 +541,9 @@ void acct_process(long exitcode)
 }
 
 
-/*
- * acct_update_integrals
- *    -  update mm integral fields in task_struct
+/**
+ * acct_update_integrals - update mm integral fields in task_struct
+ * @tsk: task_struct for accounting
  */
 void acct_update_integrals(struct task_struct *tsk)
 {
@@ -547,9 +558,9 @@ void acct_update_integrals(struct task_struct *tsk)
 	}
 }
 
-/*
- * acct_clear_integrals
- *    - clear the mm integral fields in task_struct
+/**
+ * acct_clear_integrals - clear the mm integral fields in task_struct
+ * @tsk: task_struct whose accounting fields are cleared
  */
 void acct_clear_integrals(struct task_struct *tsk)
 {
diff --git a/kernel/compat.c b/kernel/compat.c
index ddfcaaa8662..102296e21ea 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -48,8 +48,7 @@ static long compat_nanosleep_restart(struct restart_block *restart)
 	if (!time_after(expire, now))
 		return 0;
 
-	current->state = TASK_INTERRUPTIBLE;
-	expire = schedule_timeout(expire - now);
+	expire = schedule_timeout_interruptible(expire - now);
 	if (expire == 0)
 		return 0;
 
@@ -82,8 +81,7 @@ asmlinkage long compat_sys_nanosleep(struct compat_timespec __user *rqtp,
 		return -EINVAL;
 
 	expire = timespec_to_jiffies(&t) + (t.tv_sec || t.tv_nsec);
-	current->state = TASK_INTERRUPTIBLE;
-	expire = schedule_timeout(expire);
+	expire = schedule_timeout_interruptible(expire);
 	if (expire == 0)
 		return 0;
 
@@ -795,8 +793,7 @@ compat_sys_rt_sigtimedwait (compat_sigset_t __user *uthese,
 			recalc_sigpending();
 			spin_unlock_irq(&current->sighand->siglock);
 
-			current->state = TASK_INTERRUPTIBLE;
-			timeout = schedule_timeout(timeout);
+			timeout = schedule_timeout_interruptible(timeout);
 
 			spin_lock_irq(&current->sighand->siglock);
 			sig = dequeue_signal(current, &s, &info);
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 1f06e769010..79866bc6b3a 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -180,6 +180,42 @@ static struct super_block *cpuset_sb = NULL;
  */
 
 static DECLARE_MUTEX(cpuset_sem);
+static struct task_struct *cpuset_sem_owner;
+static int cpuset_sem_depth;
+
+/*
+ * The global cpuset semaphore cpuset_sem can be needed by the
+ * memory allocator to update a tasks mems_allowed (see the calls
+ * to cpuset_update_current_mems_allowed()) or to walk up the
+ * cpuset hierarchy to find a mem_exclusive cpuset see the calls
+ * to cpuset_excl_nodes_overlap()).
+ *
+ * But if the memory allocation is being done by cpuset.c code, it
+ * usually already holds cpuset_sem.  Double tripping on a kernel
+ * semaphore deadlocks the current task, and any other task that
+ * subsequently tries to obtain the lock.
+ *
+ * Run all up's and down's on cpuset_sem through the following
+ * wrappers, which will detect this nested locking, and avoid
+ * deadlocking.
+ */
+
+static inline void cpuset_down(struct semaphore *psem)
+{
+	if (cpuset_sem_owner != current) {
+		down(psem);
+		cpuset_sem_owner = current;
+	}
+	cpuset_sem_depth++;
+}
+
+static inline void cpuset_up(struct semaphore *psem)
+{
+	if (--cpuset_sem_depth == 0) {
+		cpuset_sem_owner = NULL;
+		up(psem);
+	}
+}
 
 /*
  * A couple of forward declarations required, due to cyclic reference loop:
@@ -522,19 +558,10 @@ static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask)
  * Refresh current tasks mems_allowed and mems_generation from
  * current tasks cpuset.  Call with cpuset_sem held.
  *
- * Be sure to call refresh_mems() on any cpuset operation which
- * (1) holds cpuset_sem, and (2) might possibly alloc memory.
- * Call after obtaining cpuset_sem lock, before any possible
- * allocation.  Otherwise one risks trying to allocate memory
- * while the task cpuset_mems_generation is not the same as
- * the mems_generation in its cpuset, which would deadlock on
- * cpuset_sem in cpuset_update_current_mems_allowed().
- *
- * Since we hold cpuset_sem, once refresh_mems() is called, the
- * test (current->cpuset_mems_generation != cs->mems_generation)
- * in cpuset_update_current_mems_allowed() will remain false,
- * until we drop cpuset_sem.  Anyone else who would change our
- * cpusets mems_generation needs to lock cpuset_sem first.
+ * This routine is needed to update the per-task mems_allowed
+ * data, within the tasks context, when it is trying to allocate
+ * memory (in various mm/mempolicy.c routines) and notices
+ * that some other task has been modifying its cpuset.
  */
 
 static void refresh_mems(void)
@@ -840,7 +867,7 @@ static ssize_t cpuset_common_file_write(struct file *file, const char __user *us
 	}
 	buffer[nbytes] = 0;	/* nul-terminate */
 
-	down(&cpuset_sem);
+	cpuset_down(&cpuset_sem);
 
 	if (is_removed(cs)) {
 		retval = -ENODEV;
@@ -874,7 +901,7 @@ static ssize_t cpuset_common_file_write(struct file *file, const char __user *us
 	if (retval == 0)
 		retval = nbytes;
 out2:
-	up(&cpuset_sem);
+	cpuset_up(&cpuset_sem);
 	cpuset_release_agent(pathbuf);
 out1:
 	kfree(buffer);
@@ -914,9 +941,9 @@ static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
 {
 	cpumask_t mask;
 
-	down(&cpuset_sem);
+	cpuset_down(&cpuset_sem);
 	mask = cs->cpus_allowed;
-	up(&cpuset_sem);
+	cpuset_up(&cpuset_sem);
 
 	return cpulist_scnprintf(page, PAGE_SIZE, mask);
 }
@@ -925,9 +952,9 @@ static int cpuset_sprintf_memlist(char *page, struct cpuset *cs)
 {
 	nodemask_t mask;
 
-	down(&cpuset_sem);
+	cpuset_down(&cpuset_sem);
 	mask = cs->mems_allowed;
-	up(&cpuset_sem);
+	cpuset_up(&cpuset_sem);
 
 	return nodelist_scnprintf(page, PAGE_SIZE, mask);
 }
@@ -972,6 +999,10 @@ static ssize_t cpuset_common_file_read(struct file *file, char __user *buf,
 	*s++ = '\n';
 	*s = '\0';
 
+	/* Do nothing if *ppos is at the eof or beyond the eof. */
+	if (s - page <= *ppos)
+		return 0;
+
 	start = page + *ppos;
 	n = s - start;
 	retval = n - copy_to_user(buf, start, min(n, nbytes));
@@ -1330,8 +1361,7 @@ static long cpuset_create(struct cpuset *parent, const char *name, int mode)
 	if (!cs)
 		return -ENOMEM;
 
-	down(&cpuset_sem);
-	refresh_mems();
+	cpuset_down(&cpuset_sem);
 	cs->flags = 0;
 	if (notify_on_release(parent))
 		set_bit(CS_NOTIFY_ON_RELEASE, &cs->flags);
@@ -1356,14 +1386,14 @@ static long cpuset_create(struct cpuset *parent, const char *name, int mode)
 	 * will down() this new directory's i_sem and if we race with
 	 * another mkdir, we might deadlock.
 	 */
-	up(&cpuset_sem);
+	cpuset_up(&cpuset_sem);
 
 	err = cpuset_populate_dir(cs->dentry);
 	/* If err < 0, we have a half-filled directory - oh well ;) */
 	return 0;
 err:
 	list_del(&cs->sibling);
-	up(&cpuset_sem);
+	cpuset_up(&cpuset_sem);
 	kfree(cs);
 	return err;
 }
@@ -1385,14 +1415,13 @@ static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry)
 
 	/* the vfs holds both inode->i_sem already */
 
-	down(&cpuset_sem);
-	refresh_mems();
+	cpuset_down(&cpuset_sem);
 	if (atomic_read(&cs->count) > 0) {
-		up(&cpuset_sem);
+		cpuset_up(&cpuset_sem);
 		return -EBUSY;
 	}
 	if (!list_empty(&cs->children)) {
-		up(&cpuset_sem);
+		cpuset_up(&cpuset_sem);
 		return -EBUSY;
 	}
 	parent = cs->parent;
@@ -1408,7 +1437,7 @@ static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	spin_unlock(&d->d_lock);
 	cpuset_d_remove_dir(d);
 	dput(d);
-	up(&cpuset_sem);
+	cpuset_up(&cpuset_sem);
 	cpuset_release_agent(pathbuf);
 	return 0;
 }
@@ -1511,10 +1540,10 @@ void cpuset_exit(struct task_struct *tsk)
 	if (notify_on_release(cs)) {
 		char *pathbuf = NULL;
 
-		down(&cpuset_sem);
+		cpuset_down(&cpuset_sem);
 		if (atomic_dec_and_test(&cs->count))
 			check_for_release(cs, &pathbuf);
-		up(&cpuset_sem);
+		cpuset_up(&cpuset_sem);
 		cpuset_release_agent(pathbuf);
 	} else {
 		atomic_dec(&cs->count);
@@ -1535,11 +1564,11 @@ cpumask_t cpuset_cpus_allowed(const struct task_struct *tsk)
 {
 	cpumask_t mask;
 
-	down(&cpuset_sem);
+	cpuset_down(&cpuset_sem);
 	task_lock((struct task_struct *)tsk);
 	guarantee_online_cpus(tsk->cpuset, &mask);
 	task_unlock((struct task_struct *)tsk);
-	up(&cpuset_sem);
+	cpuset_up(&cpuset_sem);
 
 	return mask;
 }
@@ -1564,9 +1593,9 @@ void cpuset_update_current_mems_allowed(void)
 	if (!cs)
 		return;		/* task is exiting */
 	if (current->cpuset_mems_generation != cs->mems_generation) {
-		down(&cpuset_sem);
+		cpuset_down(&cpuset_sem);
 		refresh_mems();
-		up(&cpuset_sem);
+		cpuset_up(&cpuset_sem);
 	}
 }
 
@@ -1665,14 +1694,14 @@ int cpuset_zone_allowed(struct zone *z, unsigned int __nocast gfp_mask)
 		return 0;
 
 	/* Not hardwall and node outside mems_allowed: scan up cpusets */
-	down(&cpuset_sem);
+	cpuset_down(&cpuset_sem);
 	cs = current->cpuset;
 	if (!cs)
 		goto done;		/* current task exiting */
 	cs = nearest_exclusive_ancestor(cs);
 	allowed = node_isset(node, cs->mems_allowed);
 done:
-	up(&cpuset_sem);
+	cpuset_up(&cpuset_sem);
 	return allowed;
 }
 
@@ -1693,7 +1722,7 @@ int cpuset_excl_nodes_overlap(const struct task_struct *p)
 	const struct cpuset *cs1, *cs2;	/* my and p's cpuset ancestors */
 	int overlap = 0;		/* do cpusets overlap? */
 
-	down(&cpuset_sem);
+	cpuset_down(&cpuset_sem);
 	cs1 = current->cpuset;
 	if (!cs1)
 		goto done;		/* current task exiting */
@@ -1704,7 +1733,7 @@ int cpuset_excl_nodes_overlap(const struct task_struct *p)
 	cs2 = nearest_exclusive_ancestor(cs2);
 	overlap = nodes_intersects(cs1->mems_allowed, cs2->mems_allowed);
 done:
-	up(&cpuset_sem);
+	cpuset_up(&cpuset_sem);
 
 	return overlap;
 }
@@ -1727,7 +1756,7 @@ static int proc_cpuset_show(struct seq_file *m, void *v)
 		return -ENOMEM;
 
 	tsk = m->private;
-	down(&cpuset_sem);
+	cpuset_down(&cpuset_sem);
 	task_lock(tsk);
 	cs = tsk->cpuset;
 	task_unlock(tsk);
@@ -1742,7 +1771,7 @@ static int proc_cpuset_show(struct seq_file *m, void *v)
 	seq_puts(m, buf);
 	seq_putc(m, '\n');
 out:
-	up(&cpuset_sem);
+	cpuset_up(&cpuset_sem);
 	kfree(buf);
 	return retval;
 }
diff --git a/kernel/exit.c b/kernel/exit.c
index 5b0fb9f09f2..6d2089a1bce 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -368,17 +368,19 @@ EXPORT_SYMBOL(daemonize);
 static inline void close_files(struct files_struct * files)
 {
 	int i, j;
+	struct fdtable *fdt;
 
 	j = 0;
+	fdt = files_fdtable(files);
 	for (;;) {
 		unsigned long set;
 		i = j * __NFDBITS;
-		if (i >= files->max_fdset || i >= files->max_fds)
+		if (i >= fdt->max_fdset || i >= fdt->max_fds)
 			break;
-		set = files->open_fds->fds_bits[j++];
+		set = fdt->open_fds->fds_bits[j++];
 		while (set) {
 			if (set & 1) {
-				struct file * file = xchg(&files->fd[i], NULL);
+				struct file * file = xchg(&fdt->fd[i], NULL);
 				if (file)
 					filp_close(file, files);
 			}
@@ -403,18 +405,22 @@ struct files_struct *get_files_struct(struct task_struct *task)
 
 void fastcall put_files_struct(struct files_struct *files)
 {
+	struct fdtable *fdt;
+
 	if (atomic_dec_and_test(&files->count)) {
 		close_files(files);
 		/*
 		 * Free the fd and fdset arrays if we expanded them.
+		 * If the fdtable was embedded, pass files for freeing
+		 * at the end of the RCU grace period. Otherwise,
+		 * you can free files immediately.
 		 */
-		if (files->fd != &files->fd_array[0])
-			free_fd_array(files->fd, files->max_fds);
-		if (files->max_fdset > __FD_SETSIZE) {
-			free_fdset(files->open_fds, files->max_fdset);
-			free_fdset(files->close_on_exec, files->max_fdset);
-		}
-		kmem_cache_free(files_cachep, files);
+		fdt = files_fdtable(files);
+		if (fdt == &files->fdtab)
+			fdt->free_files = files;
+		else
+			kmem_cache_free(files_cachep, files);
+		free_fdtable(fdt);
 	}
 }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 7e1ead9a6ba..8149f360288 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -35,6 +35,7 @@
 #include <linux/syscalls.h>
 #include <linux/jiffies.h>
 #include <linux/futex.h>
+#include <linux/rcupdate.h>
 #include <linux/ptrace.h>
 #include <linux/mount.h>
 #include <linux/audit.h>
@@ -176,6 +177,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 
 	/* One for us, one for whoever does the "release_task()" (usually parent) */
 	atomic_set(&tsk->usage,2);
+	atomic_set(&tsk->fs_excl, 0);
 	return tsk;
 }
 
@@ -564,24 +566,53 @@ static inline int copy_fs(unsigned long clone_flags, struct task_struct * tsk)
 	return 0;
 }
 
-static int count_open_files(struct files_struct *files, int size)
+static int count_open_files(struct fdtable *fdt)
 {
+	int size = fdt->max_fdset;
 	int i;
 
 	/* Find the last open fd */
 	for (i = size/(8*sizeof(long)); i > 0; ) {
-		if (files->open_fds->fds_bits[--i])
+		if (fdt->open_fds->fds_bits[--i])
 			break;
 	}
 	i = (i+1) * 8 * sizeof(long);
 	return i;
 }
 
+static struct files_struct *alloc_files(void)
+{
+	struct files_struct *newf;
+	struct fdtable *fdt;
+
+	newf = kmem_cache_alloc(files_cachep, SLAB_KERNEL);
+	if (!newf)
+		goto out;
+
+	atomic_set(&newf->count, 1);
+
+	spin_lock_init(&newf->file_lock);
+	fdt = &newf->fdtab;
+	fdt->next_fd = 0;
+	fdt->max_fds = NR_OPEN_DEFAULT;
+	fdt->max_fdset = __FD_SETSIZE;
+	fdt->close_on_exec = &newf->close_on_exec_init;
+	fdt->open_fds = &newf->open_fds_init;
+	fdt->fd = &newf->fd_array[0];
+	INIT_RCU_HEAD(&fdt->rcu);
+	fdt->free_files = NULL;
+	fdt->next = NULL;
+	rcu_assign_pointer(newf->fdt, fdt);
+out:
+	return newf;
+}
+
 static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
 {
 	struct files_struct *oldf, *newf;
 	struct file **old_fds, **new_fds;
 	int open_files, size, i, error = 0, expand;
+	struct fdtable *old_fdt, *new_fdt;
 
 	/*
 	 * A background process may not have any files ...
@@ -602,35 +633,27 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
 	 */
 	tsk->files = NULL;
 	error = -ENOMEM;
-	newf = kmem_cache_alloc(files_cachep, SLAB_KERNEL);
-	if (!newf) 
+	newf = alloc_files();
+	if (!newf)
 		goto out;
 
-	atomic_set(&newf->count, 1);
-
-	spin_lock_init(&newf->file_lock);
-	newf->next_fd	    = 0;
-	newf->max_fds	    = NR_OPEN_DEFAULT;
-	newf->max_fdset	    = __FD_SETSIZE;
-	newf->close_on_exec = &newf->close_on_exec_init;
-	newf->open_fds	    = &newf->open_fds_init;
-	newf->fd	    = &newf->fd_array[0];
-
 	spin_lock(&oldf->file_lock);
-
-	open_files = count_open_files(oldf, oldf->max_fdset);
+	old_fdt = files_fdtable(oldf);
+	new_fdt = files_fdtable(newf);
+	size = old_fdt->max_fdset;
+	open_files = count_open_files(old_fdt);
 	expand = 0;
 
 	/*
 	 * Check whether we need to allocate a larger fd array or fd set.
 	 * Note: we're not a clone task, so the open count won't  change.
 	 */
-	if (open_files > newf->max_fdset) {
-		newf->max_fdset = 0;
+	if (open_files > new_fdt->max_fdset) {
+		new_fdt->max_fdset = 0;
 		expand = 1;
 	}
-	if (open_files > newf->max_fds) {
-		newf->max_fds = 0;
+	if (open_files > new_fdt->max_fds) {
+		new_fdt->max_fds = 0;
 		expand = 1;
 	}
 
@@ -642,14 +665,21 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
 		spin_unlock(&newf->file_lock);
 		if (error < 0)
 			goto out_release;
+		new_fdt = files_fdtable(newf);
+		/*
+		 * Reacquire the oldf lock and a pointer to its fd table
+		 * who knows it may have a new bigger fd table. We need
+		 * the latest pointer.
+		 */
 		spin_lock(&oldf->file_lock);
+		old_fdt = files_fdtable(oldf);
 	}
 
-	old_fds = oldf->fd;
-	new_fds = newf->fd;
+	old_fds = old_fdt->fd;
+	new_fds = new_fdt->fd;
 
-	memcpy(newf->open_fds->fds_bits, oldf->open_fds->fds_bits, open_files/8);
-	memcpy(newf->close_on_exec->fds_bits, oldf->close_on_exec->fds_bits, open_files/8);
+	memcpy(new_fdt->open_fds->fds_bits, old_fdt->open_fds->fds_bits, open_files/8);
+	memcpy(new_fdt->close_on_exec->fds_bits, old_fdt->close_on_exec->fds_bits, open_files/8);
 
 	for (i = open_files; i != 0; i--) {
 		struct file *f = *old_fds++;
@@ -662,24 +692,24 @@ static int copy_files(unsigned long clone_flags, struct task_struct * tsk)
 			 * is partway through open().  So make sure that this
 			 * fd is available to the new process.
 			 */
-			FD_CLR(open_files - i, newf->open_fds);
+			FD_CLR(open_files - i, new_fdt->open_fds);
 		}
-		*new_fds++ = f;
+		rcu_assign_pointer(*new_fds++, f);
 	}
 	spin_unlock(&oldf->file_lock);
 
 	/* compute the remainder to be cleared */
-	size = (newf->max_fds - open_files) * sizeof(struct file *);
+	size = (new_fdt->max_fds - open_files) * sizeof(struct file *);
 
 	/* This is long word aligned thus could use a optimized version */ 
 	memset(new_fds, 0, size); 
 
-	if (newf->max_fdset > open_files) {
-		int left = (newf->max_fdset-open_files)/8;
+	if (new_fdt->max_fdset > open_files) {
+		int left = (new_fdt->max_fdset-open_files)/8;
 		int start = open_files / (8 * sizeof(unsigned long));
 
-		memset(&newf->open_fds->fds_bits[start], 0, left);
-		memset(&newf->close_on_exec->fds_bits[start], 0, left);
+		memset(&new_fdt->open_fds->fds_bits[start], 0, left);
+		memset(&new_fdt->close_on_exec->fds_bits[start], 0, left);
 	}
 
 	tsk->files = newf;
@@ -688,9 +718,9 @@ out:
 	return error;
 
 out_release:
-	free_fdset (newf->close_on_exec, newf->max_fdset);
-	free_fdset (newf->open_fds, newf->max_fdset);
-	free_fd_array(newf->fd, newf->max_fds);
+	free_fdset (new_fdt->close_on_exec, new_fdt->max_fdset);
+	free_fdset (new_fdt->open_fds, new_fdt->max_fdset);
+	free_fd_array(new_fdt->fd, new_fdt->max_fds);
 	kmem_cache_free(files_cachep, newf);
 	goto out;
 }
@@ -1115,6 +1145,9 @@ static task_t *copy_process(unsigned long clone_flags,
 			__get_cpu_var(process_counts)++;
 	}
 
+	if (!current->signal->tty && p->signal->tty)
+		p->signal->tty = NULL;
+
 	nr_threads++;
 	total_forks++;
 	write_unlock_irq(&tasklist_lock);
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index f436993bd59..bef3b6901b7 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -45,6 +45,7 @@
 #include <linux/percpu.h>
 #include <linux/notifier.h>
 #include <linux/rcupdate.h>
+#include <linux/rcuref.h>
 #include <linux/cpu.h>
 
 /* Definition for rcupdate control block. */
@@ -72,6 +73,19 @@ DEFINE_PER_CPU(struct rcu_data, rcu_bh_data) = { 0L };
 static DEFINE_PER_CPU(struct tasklet_struct, rcu_tasklet) = {NULL};
 static int maxbatch = 10;
 
+#ifndef __HAVE_ARCH_CMPXCHG
+/*
+ * We use an array of spinlocks for the rcurefs -- similar to ones in sparc
+ * 32 bit atomic_t implementations, and a hash function similar to that
+ * for our refcounting needs.
+ * Can't help multiprocessors which donot have cmpxchg :(
+ */
+
+spinlock_t __rcuref_hash[RCUREF_HASH_SIZE] = {
+	[0 ... (RCUREF_HASH_SIZE-1)] = SPIN_LOCK_UNLOCKED
+};
+#endif
+
 /**
  * call_rcu - Queue an RCU callback for invocation after a grace period.
  * @head: structure to be used for queueing the RCU updates.
diff --git a/kernel/sched.c b/kernel/sched.c
index 18b95520a2e..81b3a96ed2d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -875,7 +875,7 @@ static int migrate_task(task_t *p, int dest_cpu, migration_req_t *req)
  * smp_call_function() if an IPI is sent by the same process we are
  * waiting to become inactive.
  */
-void wait_task_inactive(task_t * p)
+void wait_task_inactive(task_t *p)
 {
 	unsigned long flags;
 	runqueue_t *rq;
@@ -966,8 +966,11 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 		int local_group;
 		int i;
 
+		/* Skip over this group if it has no CPUs allowed */
+		if (!cpus_intersects(group->cpumask, p->cpus_allowed))
+			goto nextgroup;
+
 		local_group = cpu_isset(this_cpu, group->cpumask);
-		/* XXX: put a cpus allowed check */
 
 		/* Tally up the load of all CPUs in the group */
 		avg_load = 0;
@@ -992,6 +995,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 			min_load = avg_load;
 			idlest = group;
 		}
+nextgroup:
 		group = group->next;
 	} while (group != sd->groups);
 
@@ -1003,13 +1007,18 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
 /*
  * find_idlest_queue - find the idlest runqueue among the cpus in group.
  */
-static int find_idlest_cpu(struct sched_group *group, int this_cpu)
+static int
+find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 {
+	cpumask_t tmp;
 	unsigned long load, min_load = ULONG_MAX;
 	int idlest = -1;
 	int i;
 
-	for_each_cpu_mask(i, group->cpumask) {
+	/* Traverse only the allowed CPUs */
+	cpus_and(tmp, group->cpumask, p->cpus_allowed);
+
+	for_each_cpu_mask(i, tmp) {
 		load = source_load(i, 0);
 
 		if (load < min_load || (load == min_load && i == this_cpu)) {
@@ -1052,7 +1061,7 @@ static int sched_balance_self(int cpu, int flag)
 		if (!group)
 			goto nextlevel;
 
-		new_cpu = find_idlest_cpu(group, cpu);
+		new_cpu = find_idlest_cpu(group, t, cpu);
 		if (new_cpu == -1 || new_cpu == cpu)
 			goto nextlevel;
 
@@ -1127,7 +1136,7 @@ static inline int wake_idle(int cpu, task_t *p)
  *
  * returns failure only if the task is already active.
  */
-static int try_to_wake_up(task_t * p, unsigned int state, int sync)
+static int try_to_wake_up(task_t *p, unsigned int state, int sync)
 {
 	int cpu, this_cpu, success = 0;
 	unsigned long flags;
@@ -1252,6 +1261,16 @@ out_activate:
 	}
 
 	/*
+	 * Tasks that have marked their sleep as noninteractive get
+	 * woken up without updating their sleep average. (i.e. their
+	 * sleep is handled in a priority-neutral manner, no priority
+	 * boost and no penalty.)
+	 */
+	if (old_state & TASK_NONINTERACTIVE)
+		__activate_task(p, rq);
+	else
+		activate_task(p, rq, cpu == this_cpu);
+	/*
 	 * Sync wakeups (i.e. those types of wakeups where the waker
 	 * has indicated that it will leave the CPU in short order)
 	 * don't trigger a preemption, if the woken up task will run on
@@ -1259,7 +1278,6 @@ out_activate:
 	 * the waker guarantees that the freshly woken up task is going
 	 * to be considered on this CPU.)
 	 */
-	activate_task(p, rq, cpu == this_cpu);
 	if (!sync || cpu != this_cpu) {
 		if (TASK_PREEMPTS_CURR(p, rq))
 			resched_task(rq->curr);
@@ -1274,7 +1292,7 @@ out:
 	return success;
 }
 
-int fastcall wake_up_process(task_t * p)
+int fastcall wake_up_process(task_t *p)
 {
 	return try_to_wake_up(p, TASK_STOPPED | TASK_TRACED |
 				 TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE, 0);
@@ -1353,7 +1371,7 @@ void fastcall sched_fork(task_t *p, int clone_flags)
  * that must be done for every newly created context, then puts the task
  * on the runqueue and wakes it.
  */
-void fastcall wake_up_new_task(task_t * p, unsigned long clone_flags)
+void fastcall wake_up_new_task(task_t *p, unsigned long clone_flags)
 {
 	unsigned long flags;
 	int this_cpu, cpu;
@@ -1436,7 +1454,7 @@ void fastcall wake_up_new_task(task_t * p, unsigned long clone_flags)
  * artificially, because any timeslice recovered here
  * was given away by the parent in the first place.)
  */
-void fastcall sched_exit(task_t * p)
+void fastcall sched_exit(task_t *p)
 {
 	unsigned long flags;
 	runqueue_t *rq;
@@ -1511,6 +1529,10 @@ static inline void finish_task_switch(runqueue_t *rq, task_t *prev)
 	 *		Manfred Spraul <manfred@colorfullife.com>
 	 */
 	prev_task_flags = prev->flags;
+#ifdef CONFIG_DEBUG_SPINLOCK
+	/* this is a valid case when another task releases the spinlock */
+	rq->lock.owner = current;
+#endif
 	finish_arch_switch(prev);
 	finish_lock_switch(rq, prev);
 	if (mm)
@@ -1753,7 +1775,8 @@ void pull_task(runqueue_t *src_rq, prio_array_t *src_array, task_t *p,
  */
 static inline
 int can_migrate_task(task_t *p, runqueue_t *rq, int this_cpu,
-	     struct sched_domain *sd, enum idle_type idle, int *all_pinned)
+		     struct sched_domain *sd, enum idle_type idle,
+		     int *all_pinned)
 {
 	/*
 	 * We do not migrate tasks that are:
@@ -1883,10 +1906,11 @@ out:
  */
 static struct sched_group *
 find_busiest_group(struct sched_domain *sd, int this_cpu,
-		   unsigned long *imbalance, enum idle_type idle)
+		   unsigned long *imbalance, enum idle_type idle, int *sd_idle)
 {
 	struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
 	unsigned long max_load, avg_load, total_load, this_load, total_pwr;
+	unsigned long max_pull;
 	int load_idx;
 
 	max_load = this_load = total_load = total_pwr = 0;
@@ -1908,6 +1932,9 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 		avg_load = 0;
 
 		for_each_cpu_mask(i, group->cpumask) {
+			if (*sd_idle && !idle_cpu(i))
+				*sd_idle = 0;
+
 			/* Bias balancing toward cpus of our domain */
 			if (local_group)
 				load = target_load(i, load_idx);
@@ -1933,7 +1960,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 		group = group->next;
 	} while (group != sd->groups);
 
-	if (!busiest || this_load >= max_load)
+	if (!busiest || this_load >= max_load || max_load <= SCHED_LOAD_SCALE)
 		goto out_balanced;
 
 	avg_load = (SCHED_LOAD_SCALE * total_load) / total_pwr;
@@ -1953,8 +1980,12 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 	 * by pulling tasks to us.  Be careful of negative numbers as they'll
 	 * appear as very large values with unsigned longs.
 	 */
+
+	/* Don't want to pull so many tasks that a group would go idle */
+	max_pull = min(max_load - avg_load, max_load - SCHED_LOAD_SCALE);
+
 	/* How much load to actually move to equalise the imbalance */
-	*imbalance = min((max_load - avg_load) * busiest->cpu_power,
+	*imbalance = min(max_pull * busiest->cpu_power,
 				(avg_load - this_load) * this->cpu_power)
 			/ SCHED_LOAD_SCALE;
 
@@ -2051,11 +2082,14 @@ static int load_balance(int this_cpu, runqueue_t *this_rq,
 	unsigned long imbalance;
 	int nr_moved, all_pinned = 0;
 	int active_balance = 0;
+	int sd_idle = 0;
+
+	if (idle != NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER)
+		sd_idle = 1;
 
-	spin_lock(&this_rq->lock);
 	schedstat_inc(sd, lb_cnt[idle]);
 
-	group = find_busiest_group(sd, this_cpu, &imbalance, idle);
+	group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle);
 	if (!group) {
 		schedstat_inc(sd, lb_nobusyg[idle]);
 		goto out_balanced;
@@ -2079,19 +2113,16 @@ static int load_balance(int this_cpu, runqueue_t *this_rq,
 		 * still unbalanced. nr_moved simply stays zero, so it is
 		 * correctly treated as an imbalance.
 		 */
-		double_lock_balance(this_rq, busiest);
+		double_rq_lock(this_rq, busiest);
 		nr_moved = move_tasks(this_rq, this_cpu, busiest,
-						imbalance, sd, idle,
-						&all_pinned);
-		spin_unlock(&busiest->lock);
+					imbalance, sd, idle, &all_pinned);
+		double_rq_unlock(this_rq, busiest);
 
 		/* All tasks on this runqueue were pinned by CPU affinity */
 		if (unlikely(all_pinned))
 			goto out_balanced;
 	}
 
-	spin_unlock(&this_rq->lock);
-
 	if (!nr_moved) {
 		schedstat_inc(sd, lb_failed[idle]);
 		sd->nr_balance_failed++;
@@ -2099,6 +2130,16 @@ static int load_balance(int this_cpu, runqueue_t *this_rq,
 		if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {
 
 			spin_lock(&busiest->lock);
+
+			/* don't kick the migration_thread, if the curr
+			 * task on busiest cpu can't be moved to this_cpu
+			 */
+			if (!cpu_isset(this_cpu, busiest->curr->cpus_allowed)) {
+				spin_unlock(&busiest->lock);
+				all_pinned = 1;
+				goto out_one_pinned;
+			}
+
 			if (!busiest->active_balance) {
 				busiest->active_balance = 1;
 				busiest->push_cpu = this_cpu;
@@ -2131,19 +2172,23 @@ static int load_balance(int this_cpu, runqueue_t *this_rq,
 			sd->balance_interval *= 2;
 	}
 
+	if (!nr_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER)
+		return -1;
 	return nr_moved;
 
 out_balanced:
-	spin_unlock(&this_rq->lock);
-
 	schedstat_inc(sd, lb_balanced[idle]);
 
 	sd->nr_balance_failed = 0;
+
+out_one_pinned:
 	/* tune up the balancing interval */
 	if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
 			(sd->balance_interval < sd->max_interval))
 		sd->balance_interval *= 2;
 
+	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER)
+		return -1;
 	return 0;
 }
 
@@ -2161,9 +2206,13 @@ static int load_balance_newidle(int this_cpu, runqueue_t *this_rq,
 	runqueue_t *busiest = NULL;
 	unsigned long imbalance;
 	int nr_moved = 0;
+	int sd_idle = 0;
+
+	if (sd->flags & SD_SHARE_CPUPOWER)
+		sd_idle = 1;
 
 	schedstat_inc(sd, lb_cnt[NEWLY_IDLE]);
-	group = find_busiest_group(sd, this_cpu, &imbalance, NEWLY_IDLE);
+	group = find_busiest_group(sd, this_cpu, &imbalance, NEWLY_IDLE, &sd_idle);
 	if (!group) {
 		schedstat_inc(sd, lb_nobusyg[NEWLY_IDLE]);
 		goto out_balanced;
@@ -2177,22 +2226,30 @@ static int load_balance_newidle(int this_cpu, runqueue_t *this_rq,
 
 	BUG_ON(busiest == this_rq);
 
-	/* Attempt to move tasks */
-	double_lock_balance(this_rq, busiest);
-
 	schedstat_add(sd, lb_imbalance[NEWLY_IDLE], imbalance);
-	nr_moved = move_tasks(this_rq, this_cpu, busiest,
+
+	nr_moved = 0;
+	if (busiest->nr_running > 1) {
+		/* Attempt to move tasks */
+		double_lock_balance(this_rq, busiest);
+		nr_moved = move_tasks(this_rq, this_cpu, busiest,
 					imbalance, sd, NEWLY_IDLE, NULL);
-	if (!nr_moved)
+		spin_unlock(&busiest->lock);
+	}
+
+	if (!nr_moved) {
 		schedstat_inc(sd, lb_failed[NEWLY_IDLE]);
-	else
+		if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER)
+			return -1;
+	} else
 		sd->nr_balance_failed = 0;
 
-	spin_unlock(&busiest->lock);
 	return nr_moved;
 
 out_balanced:
 	schedstat_inc(sd, lb_balanced[NEWLY_IDLE]);
+	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER)
+		return -1;
 	sd->nr_balance_failed = 0;
 	return 0;
 }
@@ -2317,7 +2374,11 @@ static void rebalance_tick(int this_cpu, runqueue_t *this_rq,
 
 		if (j - sd->last_balance >= interval) {
 			if (load_balance(this_cpu, this_rq, sd, idle)) {
-				/* We've pulled tasks over so no longer idle */
+				/*
+				 * We've pulled tasks over so either we're no
+				 * longer idle, or one of our SMT siblings is
+				 * not idle.
+				 */
 				idle = NOT_IDLE;
 			}
 			sd->last_balance += interval;
@@ -2576,6 +2637,13 @@ out:
 }
 
 #ifdef CONFIG_SCHED_SMT
+static inline void wakeup_busy_runqueue(runqueue_t *rq)
+{
+	/* If an SMT runqueue is sleeping due to priority reasons wake it up */
+	if (rq->curr == rq->idle && rq->nr_running)
+		resched_task(rq->idle);
+}
+
 static inline void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
 {
 	struct sched_domain *tmp, *sd = NULL;
@@ -2609,12 +2677,7 @@ static inline void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
 	for_each_cpu_mask(i, sibling_map) {
 		runqueue_t *smt_rq = cpu_rq(i);
 
-		/*
-		 * If an SMT sibling task is sleeping due to priority
-		 * reasons wake it up now.
-		 */
-		if (smt_rq->curr == smt_rq->idle && smt_rq->nr_running)
-			resched_task(smt_rq->idle);
+		wakeup_busy_runqueue(smt_rq);
 	}
 
 	for_each_cpu_mask(i, sibling_map)
@@ -2625,6 +2688,16 @@ static inline void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
 	 */
 }
 
+/*
+ * number of 'lost' timeslices this task wont be able to fully
+ * utilize, if another task runs on a sibling. This models the
+ * slowdown effect of other tasks running on siblings:
+ */
+static inline unsigned long smt_slice(task_t *p, struct sched_domain *sd)
+{
+	return p->time_slice * (100 - sd->per_cpu_gain) / 100;
+}
+
 static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
 {
 	struct sched_domain *tmp, *sd = NULL;
@@ -2668,6 +2741,10 @@ static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
 		runqueue_t *smt_rq = cpu_rq(i);
 		task_t *smt_curr = smt_rq->curr;
 
+		/* Kernel threads do not participate in dependent sleeping */
+		if (!p->mm || !smt_curr->mm || rt_task(p))
+			goto check_smt_task;
+
 		/*
 		 * If a user task with lower static priority than the
 		 * running task on the SMT sibling is trying to schedule,
@@ -2676,21 +2753,45 @@ static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
 		 * task from using an unfair proportion of the
 		 * physical cpu's resources. -ck
 		 */
-		if (((smt_curr->time_slice * (100 - sd->per_cpu_gain) / 100) >
-			task_timeslice(p) || rt_task(smt_curr)) &&
-			p->mm && smt_curr->mm && !rt_task(p))
-				ret = 1;
+		if (rt_task(smt_curr)) {
+			/*
+			 * With real time tasks we run non-rt tasks only
+			 * per_cpu_gain% of the time.
+			 */
+			if ((jiffies % DEF_TIMESLICE) >
+				(sd->per_cpu_gain * DEF_TIMESLICE / 100))
+					ret = 1;
+		} else
+			if (smt_curr->static_prio < p->static_prio &&
+				!TASK_PREEMPTS_CURR(p, smt_rq) &&
+				smt_slice(smt_curr, sd) > task_timeslice(p))
+					ret = 1;
+
+check_smt_task:
+		if ((!smt_curr->mm && smt_curr != smt_rq->idle) ||
+			rt_task(smt_curr))
+				continue;
+		if (!p->mm) {
+			wakeup_busy_runqueue(smt_rq);
+			continue;
+		}
 
 		/*
-		 * Reschedule a lower priority task on the SMT sibling,
-		 * or wake it up if it has been put to sleep for priority
-		 * reasons.
+		 * Reschedule a lower priority task on the SMT sibling for
+		 * it to be put to sleep, or wake it up if it has been put to
+		 * sleep for priority reasons to see if it should run now.
 		 */
-		if ((((p->time_slice * (100 - sd->per_cpu_gain) / 100) >
-			task_timeslice(smt_curr) || rt_task(p)) &&
-			smt_curr->mm && p->mm && !rt_task(smt_curr)) ||
-			(smt_curr == smt_rq->idle && smt_rq->nr_running))
-				resched_task(smt_curr);
+		if (rt_task(p)) {
+			if ((jiffies % DEF_TIMESLICE) >
+				(sd->per_cpu_gain * DEF_TIMESLICE / 100))
+					resched_task(smt_curr);
+		} else {
+			if (TASK_PREEMPTS_CURR(p, smt_rq) &&
+				smt_slice(p, sd) > task_timeslice(smt_curr))
+					resched_task(smt_curr);
+			else
+				wakeup_busy_runqueue(smt_rq);
+		}
 	}
 out_unlock:
 	for_each_cpu_mask(i, sibling_map)
@@ -2888,6 +2989,7 @@ switch_tasks:
 	if (next == rq->idle)
 		schedstat_inc(rq, sched_goidle);
 	prefetch(next);
+	prefetch_stack(next);
 	clear_tsk_need_resched(prev);
 	rcu_qsctr_inc(task_cpu(prev));
 
@@ -3015,7 +3117,8 @@ need_resched:
 
 #endif /* CONFIG_PREEMPT */
 
-int default_wake_function(wait_queue_t *curr, unsigned mode, int sync, void *key)
+int default_wake_function(wait_queue_t *curr, unsigned mode, int sync,
+			  void *key)
 {
 	task_t *p = curr->private;
 	return try_to_wake_up(p, mode, sync);
@@ -3057,7 +3160,7 @@ static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
  * @key: is directly passed to the wakeup function
  */
 void fastcall __wake_up(wait_queue_head_t *q, unsigned int mode,
-				int nr_exclusive, void *key)
+			int nr_exclusive, void *key)
 {
 	unsigned long flags;
 
@@ -3089,7 +3192,8 @@ void fastcall __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
  *
  * On UP it can prevent extra preemption.
  */
-void fastcall __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+void fastcall
+__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
 {
 	unsigned long flags;
 	int sync = 1;
@@ -3280,7 +3384,8 @@ void fastcall __sched interruptible_sleep_on(wait_queue_head_t *q)
 
 EXPORT_SYMBOL(interruptible_sleep_on);
 
-long fastcall __sched interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
+long fastcall __sched
+interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
 {
 	SLEEP_ON_VAR
 
@@ -3499,7 +3604,8 @@ static void __setscheduler(struct task_struct *p, int policy, int prio)
  * @policy: new policy.
  * @param: structure containing the new RT priority.
  */
-int sched_setscheduler(struct task_struct *p, int policy, struct sched_param *param)
+int sched_setscheduler(struct task_struct *p, int policy,
+		       struct sched_param *param)
 {
 	int retval;
 	int oldprio, oldpolicy = -1;
@@ -3519,7 +3625,7 @@ recheck:
 	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL is 0.
 	 */
 	if (param->sched_priority < 0 ||
-	    (p->mm &&  param->sched_priority > MAX_USER_RT_PRIO-1) ||
+	    (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
 	    (!p->mm && param->sched_priority > MAX_RT_PRIO-1))
 		return -EINVAL;
 	if ((policy == SCHED_NORMAL) != (param->sched_priority == 0))
@@ -3582,7 +3688,8 @@ recheck:
 }
 EXPORT_SYMBOL_GPL(sched_setscheduler);
 
-static int do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
+static int
+do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 {
 	int retval;
 	struct sched_param lparam;
@@ -3849,7 +3956,7 @@ asmlinkage long sys_sched_yield(void)
 	if (rt_task(current))
 		target = rq->active;
 
-	if (current->array->nr_active == 1) {
+	if (array->nr_active == 1) {
 		schedstat_inc(rq, yld_act_empty);
 		if (!rq->expired->nr_active)
 			schedstat_inc(rq, yld_both_empty);
@@ -3913,7 +4020,7 @@ EXPORT_SYMBOL(cond_resched);
  * operations here to prevent schedule() from being called twice (once via
  * spin_unlock(), once by hand).
  */
-int cond_resched_lock(spinlock_t * lock)
+int cond_resched_lock(spinlock_t *lock)
 {
 	int ret = 0;
 
@@ -4096,7 +4203,7 @@ static inline struct task_struct *younger_sibling(struct task_struct *p)
 	return list_entry(p->sibling.next,struct task_struct,sibling);
 }
 
-static void show_task(task_t * p)
+static void show_task(task_t *p)
 {
 	task_t *relative;
 	unsigned state;
@@ -4122,7 +4229,7 @@ static void show_task(task_t * p)
 #endif
 #ifdef CONFIG_DEBUG_STACK_USAGE
 	{
-		unsigned long * n = (unsigned long *) (p->thread_info+1);
+		unsigned long *n = (unsigned long *) (p->thread_info+1);
 		while (!*n)
 			n++;
 		free = (unsigned long) n - (unsigned long)(p->thread_info+1);
@@ -4331,7 +4438,7 @@ out:
  * thread migration by bumping thread off CPU then 'pushing' onto
  * another runqueue.
  */
-static int migration_thread(void * data)
+static int migration_thread(void *data)
 {
 	runqueue_t *rq;
 	int cpu = (long)data;
@@ -5495,3 +5602,47 @@ void normalize_rt_tasks(void)
 }
 
 #endif /* CONFIG_MAGIC_SYSRQ */
+
+#ifdef CONFIG_IA64
+/*
+ * These functions are only useful for the IA64 MCA handling.
+ *
+ * They can only be called when the whole system has been
+ * stopped - every CPU needs to be quiescent, and no scheduling
+ * activity can take place. Using them for anything else would
+ * be a serious bug, and as a result, they aren't even visible
+ * under any other configuration.
+ */
+
+/**
+ * curr_task - return the current task for a given cpu.
+ * @cpu: the processor in question.
+ *
+ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
+ */
+task_t *curr_task(int cpu)
+{
+	return cpu_curr(cpu);
+}
+
+/**
+ * set_curr_task - set the current task for a given cpu.
+ * @cpu: the processor in question.
+ * @p: the task pointer to set.
+ *
+ * Description: This function must only be used when non-maskable interrupts
+ * are serviced on a separate stack.  It allows the architecture to switch the
+ * notion of the current task on a cpu in a non-blocking manner.  This function
+ * must be called with all CPU's synchronized, and interrupts disabled, the
+ * and caller must save the original value of the current task (see
+ * curr_task() above) and restore that value before reenabling interrupts and
+ * re-starting the system.
+ *
+ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
+ */
+void set_curr_task(int cpu, task_t *p)
+{
+	cpu_curr(cpu) = p;
+}
+
+#endif
diff --git a/kernel/signal.c b/kernel/signal.c
index 4980a073237..b92c3c9f8b9 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2221,8 +2221,7 @@ sys_rt_sigtimedwait(const sigset_t __user *uthese,
 			recalc_sigpending();
 			spin_unlock_irq(&current->sighand->siglock);
 
-			current->state = TASK_INTERRUPTIBLE;
-			timeout = schedule_timeout(timeout);
+			timeout = schedule_timeout_interruptible(timeout);
 
 			try_to_freeze();
 			spin_lock_irq(&current->sighand->siglock);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index b4ab6af1dea..f766b2fc48b 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -84,7 +84,7 @@ asmlinkage void __do_softirq(void)
 	cpu = smp_processor_id();
 restart:
 	/* Reset the pending bitmask before enabling irqs */
-	local_softirq_pending() = 0;
+	set_softirq_pending(0);
 
 	local_irq_enable();
 
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index 0c3f9d8bbe1..0375fcd5921 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -3,7 +3,10 @@
  *
  * Author: Zwane Mwaikambo <zwane@fsmlabs.com>
  *
- * Copyright (2004) Ingo Molnar
+ * Copyright (2004, 2005) Ingo Molnar
+ *
+ * This file contains the spinlock/rwlock implementations for the
+ * SMP and the DEBUG_SPINLOCK cases. (UP-nondebug inlines them)
  */
 
 #include <linux/config.h>
@@ -17,12 +20,12 @@
  * Generic declaration of the raw read_trylock() function,
  * architectures are supposed to optimize this:
  */
-int __lockfunc generic_raw_read_trylock(rwlock_t *lock)
+int __lockfunc generic__raw_read_trylock(raw_rwlock_t *lock)
 {
-	_raw_read_lock(lock);
+	__raw_read_lock(lock);
 	return 1;
 }
-EXPORT_SYMBOL(generic_raw_read_trylock);
+EXPORT_SYMBOL(generic__raw_read_trylock);
 
 int __lockfunc _spin_trylock(spinlock_t *lock)
 {
@@ -57,7 +60,7 @@ int __lockfunc _write_trylock(rwlock_t *lock)
 }
 EXPORT_SYMBOL(_write_trylock);
 
-#ifndef CONFIG_PREEMPT
+#if !defined(CONFIG_PREEMPT) || !defined(CONFIG_SMP)
 
 void __lockfunc _read_lock(rwlock_t *lock)
 {
@@ -72,7 +75,7 @@ unsigned long __lockfunc _spin_lock_irqsave(spinlock_t *lock)
 
 	local_irq_save(flags);
 	preempt_disable();
-	_raw_spin_lock_flags(lock, flags);
+	_raw_spin_lock_flags(lock, &flags);
 	return flags;
 }
 EXPORT_SYMBOL(_spin_lock_irqsave);
diff --git a/kernel/timer.c b/kernel/timer.c
index 13e2b513be0..f4152fcd9f8 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1154,6 +1154,20 @@ fastcall signed long __sched schedule_timeout(signed long timeout)
 
 EXPORT_SYMBOL(schedule_timeout);
 
+signed long __sched schedule_timeout_interruptible(signed long timeout)
+{
+       set_current_state(TASK_INTERRUPTIBLE);
+       return schedule_timeout(timeout);
+}
+EXPORT_SYMBOL(schedule_timeout_interruptible);
+
+signed long __sched schedule_timeout_uninterruptible(signed long timeout)
+{
+       set_current_state(TASK_UNINTERRUPTIBLE);
+       return schedule_timeout(timeout);
+}
+EXPORT_SYMBOL(schedule_timeout_uninterruptible);
+
 /* Thread ID - the internal kernel "pid" */
 asmlinkage long sys_gettid(void)
 {
@@ -1170,8 +1184,7 @@ static long __sched nanosleep_restart(struct restart_block *restart)
 	if (!time_after(expire, now))
 		return 0;
 
-	current->state = TASK_INTERRUPTIBLE;
-	expire = schedule_timeout(expire - now);
+	expire = schedule_timeout_interruptible(expire - now);
 
 	ret = 0;
 	if (expire) {
@@ -1199,8 +1212,7 @@ asmlinkage long sys_nanosleep(struct timespec __user *rqtp, struct timespec __us
 		return -EINVAL;
 
 	expire = timespec_to_jiffies(&t) + (t.tv_sec || t.tv_nsec);
-	current->state = TASK_INTERRUPTIBLE;
-	expire = schedule_timeout(expire);
+	expire = schedule_timeout_interruptible(expire);
 
 	ret = 0;
 	if (expire) {
@@ -1598,10 +1610,8 @@ void msleep(unsigned int msecs)
 {
 	unsigned long timeout = msecs_to_jiffies(msecs) + 1;
 
-	while (timeout) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		timeout = schedule_timeout(timeout);
-	}
+	while (timeout)
+		timeout = schedule_timeout_uninterruptible(timeout);
 }
 
 EXPORT_SYMBOL(msleep);
@@ -1614,10 +1624,8 @@ unsigned long msleep_interruptible(unsigned int msecs)
 {
 	unsigned long timeout = msecs_to_jiffies(msecs) + 1;
 
-	while (timeout && !signal_pending(current)) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		timeout = schedule_timeout(timeout);
-	}
+	while (timeout && !signal_pending(current))
+		timeout = schedule_timeout_interruptible(timeout);
 	return jiffies_to_msecs(timeout);
 }