Merge /home/trondmy/scm/kernel/git/torvalds/linux-2.6

11 files changed, 101 insertions, 49 deletions

diff --git a/kernel/audit.c b/kernel/audit.c
index 83096b67510..aefa73a8a58 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -560,7 +560,7 @@ static void audit_buffer_free(struct audit_buffer *ab)
 }
 
 static struct audit_buffer * audit_buffer_alloc(struct audit_context *ctx,
-						unsigned int __nocast gfp_mask, int type)
+						gfp_t gfp_mask, int type)
 {
 	unsigned long flags;
 	struct audit_buffer *ab = NULL;
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 79866bc6b3a..28176d083f7 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -968,8 +968,6 @@ static ssize_t cpuset_common_file_read(struct file *file, char __user *buf,
 	char *page;
 	ssize_t retval = 0;
 	char *s;
-	char *start;
-	size_t n;
 
 	if (!(page = (char *)__get_free_page(GFP_KERNEL)))
 		return -ENOMEM;
@@ -999,14 +997,7 @@ 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));
-	*ppos += retval;
+	retval = simple_read_from_buffer(buf, nbytes, ppos, page, s - page);
 out:
 	free_page((unsigned long)page);
 	return retval;
@@ -1679,7 +1670,7 @@ static const struct cpuset *nearest_exclusive_ancestor(const struct cpuset *cs)
  *	GFP_USER     - only nodes in current tasks mems allowed ok.
  **/
 
-int cpuset_zone_allowed(struct zone *z, unsigned int __nocast gfp_mask)
+int cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
 {
 	int node;			/* node that zone z is on */
 	const struct cpuset *cs;	/* current cpuset ancestors */
diff --git a/kernel/exit.c b/kernel/exit.c
index ee6d8b8abef..43077732619 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1203,7 +1203,7 @@ static int wait_task_stopped(task_t *p, int delayed_group_leader, int noreap,
 
 		exit_code = p->exit_code;
 		if (unlikely(!exit_code) ||
-		    unlikely(p->state > TASK_STOPPED))
+		    unlikely(p->state & TASK_TRACED))
 			goto bail_ref;
 		return wait_noreap_copyout(p, pid, uid,
 					   why, (exit_code << 8) | 0x7f,
diff --git a/kernel/kfifo.c b/kernel/kfifo.c
index 179baafcdd9..64ab045c3d9 100644
--- a/kernel/kfifo.c
+++ b/kernel/kfifo.c
@@ -36,7 +36,7 @@
  * struct kfifo with kfree().
  */
 struct kfifo *kfifo_init(unsigned char *buffer, unsigned int size,
-			 unsigned int __nocast gfp_mask, spinlock_t *lock)
+			 gfp_t gfp_mask, spinlock_t *lock)
 {
 	struct kfifo *fifo;
 
@@ -64,7 +64,7 @@ EXPORT_SYMBOL(kfifo_init);
  *
  * The size will be rounded-up to a power of 2.
  */
-struct kfifo *kfifo_alloc(unsigned int size, unsigned int __nocast gfp_mask, spinlock_t *lock)
+struct kfifo *kfifo_alloc(unsigned int size, gfp_t gfp_mask, spinlock_t *lock)
 {
 	unsigned char *buffer;
 	struct kfifo *ret;
diff --git a/kernel/params.c b/kernel/params.c
index fbf173215fd..1a8614bac5d 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -80,8 +80,6 @@ static char *next_arg(char *args, char **param, char **val)
 	int in_quote = 0, quoted = 0;
 	char *next;
 
-	/* Chew any extra spaces */
-	while (*args == ' ') args++;
 	if (*args == '"') {
 		args++;
 		in_quote = 1;
@@ -121,6 +119,10 @@ static char *next_arg(char *args, char **param, char **val)
 		next = args + i + 1;
 	} else
 		next = args + i;
+
+	/* Chew up trailing spaces. */
+	while (*next == ' ')
+		next++;
 	return next;
 }
 
@@ -135,6 +137,10 @@ int parse_args(const char *name,
 
 	DEBUGP("Parsing ARGS: %s\n", args);
 
+	/* Chew leading spaces */
+	while (*args == ' ')
+		args++;
+
 	while (*args) {
 		int ret;
 
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index ad85d3f0dcc..7a51a5597c3 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -424,6 +424,7 @@ static void cleanup_timers(struct list_head *head,
 	cputime_t ptime = cputime_add(utime, stime);
 
 	list_for_each_entry_safe(timer, next, head, entry) {
+		put_task_struct(timer->task);
 		timer->task = NULL;
 		list_del_init(&timer->entry);
 		if (cputime_lt(timer->expires.cpu, ptime)) {
@@ -436,6 +437,7 @@ static void cleanup_timers(struct list_head *head,
 
 	++head;
 	list_for_each_entry_safe(timer, next, head, entry) {
+		put_task_struct(timer->task);
 		timer->task = NULL;
 		list_del_init(&timer->entry);
 		if (cputime_lt(timer->expires.cpu, utime)) {
@@ -448,6 +450,7 @@ static void cleanup_timers(struct list_head *head,
 
 	++head;
 	list_for_each_entry_safe(timer, next, head, entry) {
+		put_task_struct(timer->task);
 		timer->task = NULL;
 		list_del_init(&timer->entry);
 		if (timer->expires.sched < sched_time) {
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 9c9167d910d..6748de23e83 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -9,6 +9,9 @@
 #define SUSPEND_CONSOLE	(MAX_NR_CONSOLES-1)
 #endif
 
+#define MAX_PBES	((PAGE_SIZE - sizeof(struct new_utsname) \
+			- 4 - 3*sizeof(unsigned long) - sizeof(int) \
+			- sizeof(void *)) / sizeof(swp_entry_t))
 
 struct swsusp_info {
 	struct new_utsname	uts;
@@ -18,7 +21,7 @@ struct swsusp_info {
 	unsigned long		image_pages;
 	unsigned long		pagedir_pages;
 	suspend_pagedir_t	* suspend_pagedir;
-	swp_entry_t		pagedir[768];
+	swp_entry_t		pagedir[MAX_PBES];
 } __attribute__((aligned(PAGE_SIZE)));
 
 
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index 1cc9ff25e47..2d5c4567644 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -402,15 +402,14 @@ static int write_page(unsigned long addr, swp_entry_t * loc)
 static void data_free(void)
 {
 	swp_entry_t entry;
-	int i;
+	struct pbe * p;
 
-	for (i = 0; i < nr_copy_pages; i++) {
-		entry = (pagedir_nosave + i)->swap_address;
+	for_each_pbe(p, pagedir_nosave) {
+		entry = p->swap_address;
 		if (entry.val)
 			swap_free(entry);
 		else
 			break;
-		(pagedir_nosave + i)->swap_address = (swp_entry_t){0};
 	}
 }
 
@@ -932,6 +931,10 @@ static int swsusp_alloc(void)
 	if (!enough_swap())
 		return -ENOSPC;
 
+	if (MAX_PBES < nr_copy_pages / PBES_PER_PAGE +
+	    !!(nr_copy_pages % PBES_PER_PAGE))
+		return -ENOSPC;
+
 	if (!(pagedir_save = alloc_pagedir(nr_copy_pages))) {
 		printk(KERN_ERR "suspend: Allocating pagedir failed.\n");
 		return -ENOMEM;
@@ -1092,7 +1095,7 @@ static inline void eat_page(void *page)
 	*eaten_memory = c;
 }
 
-static unsigned long get_usable_page(unsigned gfp_mask)
+unsigned long get_usable_page(unsigned gfp_mask)
 {
 	unsigned long m;
 
@@ -1106,7 +1109,7 @@ static unsigned long get_usable_page(unsigned gfp_mask)
 	return m;
 }
 
-static void free_eaten_memory(void)
+void free_eaten_memory(void)
 {
 	unsigned long m;
 	void **c;
@@ -1438,9 +1441,9 @@ static int read_pagedir(struct pbe *pblist)
 	}
 
 	if (error)
-		free_page((unsigned long)pblist);
-
-	BUG_ON(i != swsusp_info.pagedir_pages);
+		free_pagedir(pblist);
+	else
+		BUG_ON(i != swsusp_info.pagedir_pages);
 
 	return error;
 }
@@ -1478,11 +1481,12 @@ static int read_suspend_image(void)
 	/* Allocate memory for the image and read the data from swap */
 
 	error = check_pagedir(pagedir_nosave);
-	free_eaten_memory();
+
 	if (!error)
 		error = data_read(pagedir_nosave);
 
 	if (error) { /* We fail cleanly */
+		free_eaten_memory();
 		for_each_pbe (p, pagedir_nosave)
 			if (p->address) {
 				free_page(p->address);
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index bef3b6901b7..2559d4b8f23 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -71,7 +71,7 @@ DEFINE_PER_CPU(struct rcu_data, rcu_bh_data) = { 0L };
 
 /* Fake initialization required by compiler */
 static DEFINE_PER_CPU(struct tasklet_struct, rcu_tasklet) = {NULL};
-static int maxbatch = 10;
+static int maxbatch = 10000;
 
 #ifndef __HAVE_ARCH_CMPXCHG
 /*
@@ -109,6 +109,10 @@ void fastcall call_rcu(struct rcu_head *head,
 	rdp = &__get_cpu_var(rcu_data);
 	*rdp->nxttail = head;
 	rdp->nxttail = &head->next;
+
+	if (unlikely(++rdp->count > 10000))
+		set_need_resched();
+
 	local_irq_restore(flags);
 }
 
@@ -140,6 +144,12 @@ void fastcall call_rcu_bh(struct rcu_head *head,
 	rdp = &__get_cpu_var(rcu_bh_data);
 	*rdp->nxttail = head;
 	rdp->nxttail = &head->next;
+	rdp->count++;
+/*
+ *  Should we directly call rcu_do_batch() here ?
+ *  if (unlikely(rdp->count > 10000))
+ *      rcu_do_batch(rdp);
+ */
 	local_irq_restore(flags);
 }
 
@@ -157,6 +167,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 		next = rdp->donelist = list->next;
 		list->func(list);
 		list = next;
+		rdp->count--;
 		if (++count >= maxbatch)
 			break;
 	}
diff --git a/kernel/signal.c b/kernel/signal.c
index b92c3c9f8b9..50c99264377 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -262,7 +262,7 @@ next_signal(struct sigpending *pending, sigset_t *mask)
 	return sig;
 }
 
-static struct sigqueue *__sigqueue_alloc(struct task_struct *t, unsigned int __nocast flags,
+static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags,
 					 int override_rlimit)
 {
 	struct sigqueue *q = NULL;
@@ -578,7 +578,8 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
  		 * is to alert stop-signal processing code when another
  		 * processor has come along and cleared the flag.
  		 */
- 		tsk->signal->flags |= SIGNAL_STOP_DEQUEUED;
+ 		if (!(tsk->signal->flags & SIGNAL_GROUP_EXIT))
+ 			tsk->signal->flags |= SIGNAL_STOP_DEQUEUED;
  	}
 	if ( signr &&
 	     ((info->si_code & __SI_MASK) == __SI_TIMER) &&
@@ -936,34 +937,31 @@ force_sig_specific(int sig, struct task_struct *t)
  * as soon as they're available, so putting the signal on the shared queue
  * will be equivalent to sending it to one such thread.
  */
-#define wants_signal(sig, p, mask) 			\
-	(!sigismember(&(p)->blocked, sig)		\
-	 && !((p)->state & mask)			\
-	 && !((p)->flags & PF_EXITING)			\
-	 && (task_curr(p) || !signal_pending(p)))
-
+static inline int wants_signal(int sig, struct task_struct *p)
+{
+	if (sigismember(&p->blocked, sig))
+		return 0;
+	if (p->flags & PF_EXITING)
+		return 0;
+	if (sig == SIGKILL)
+		return 1;
+	if (p->state & (TASK_STOPPED | TASK_TRACED))
+		return 0;
+	return task_curr(p) || !signal_pending(p);
+}
 
 static void
 __group_complete_signal(int sig, struct task_struct *p)
 {
-	unsigned int mask;
 	struct task_struct *t;
 
 	/*
-	 * Don't bother traced and stopped tasks (but
-	 * SIGKILL will punch through that).
-	 */
-	mask = TASK_STOPPED | TASK_TRACED;
-	if (sig == SIGKILL)
-		mask = 0;
-
-	/*
 	 * Now find a thread we can wake up to take the signal off the queue.
 	 *
 	 * If the main thread wants the signal, it gets first crack.
 	 * Probably the least surprising to the average bear.
 	 */
-	if (wants_signal(sig, p, mask))
+	if (wants_signal(sig, p))
 		t = p;
 	else if (thread_group_empty(p))
 		/*
@@ -981,7 +979,7 @@ __group_complete_signal(int sig, struct task_struct *p)
 			t = p->signal->curr_target = p;
 		BUG_ON(t->tgid != p->tgid);
 
-		while (!wants_signal(sig, t, mask)) {
+		while (!wants_signal(sig, t)) {
 			t = next_thread(t);
 			if (t == p->signal->curr_target)
 				/*
@@ -1195,6 +1193,40 @@ kill_proc_info(int sig, struct siginfo *info, pid_t pid)
 	return error;
 }
 
+/* like kill_proc_info(), but doesn't use uid/euid of "current" */
+int kill_proc_info_as_uid(int sig, struct siginfo *info, pid_t pid,
+		      uid_t uid, uid_t euid)
+{
+	int ret = -EINVAL;
+	struct task_struct *p;
+
+	if (!valid_signal(sig))
+		return ret;
+
+	read_lock(&tasklist_lock);
+	p = find_task_by_pid(pid);
+	if (!p) {
+		ret = -ESRCH;
+		goto out_unlock;
+	}
+	if ((!info || ((unsigned long)info != 1 &&
+			(unsigned long)info != 2 && SI_FROMUSER(info)))
+	    && (euid != p->suid) && (euid != p->uid)
+	    && (uid != p->suid) && (uid != p->uid)) {
+		ret = -EPERM;
+		goto out_unlock;
+	}
+	if (sig && p->sighand) {
+		unsigned long flags;
+		spin_lock_irqsave(&p->sighand->siglock, flags);
+		ret = __group_send_sig_info(sig, info, p);
+		spin_unlock_irqrestore(&p->sighand->siglock, flags);
+	}
+out_unlock:
+	read_unlock(&tasklist_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kill_proc_info_as_uid);
 
 /*
  * kill_something_info() interprets pid in interesting ways just like kill(2).
@@ -1766,7 +1798,8 @@ do_signal_stop(int signr)
 				 * stop is always done with the siglock held,
 				 * so this check has no races.
 				 */
-				if (t->state < TASK_STOPPED) {
+				if (!t->exit_state &&
+				    !(t->state & (TASK_STOPPED|TASK_TRACED))) {
 					stop_count++;
 					signal_wake_up(t, 0);
 				}
diff --git a/kernel/time.c b/kernel/time.c
index dd5ae1162a8..40c2410ac99 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -570,6 +570,7 @@ void getnstimeofday(struct timespec *tv)
 	tv->tv_sec = x.tv_sec;
 	tv->tv_nsec = x.tv_usec * NSEC_PER_USEC;
 }
+EXPORT_SYMBOL_GPL(getnstimeofday);
 #endif
 
 #if (BITS_PER_LONG < 64)