Merge bk://ldm.bkbits.net/linux-2.5-power

into bambi.(none):/home/mochel/src/kernel/devel/linux-2.5-power

8 files changed, 71 insertions, 67 deletions

diff --git a/kernel/compat.c b/kernel/compat.c
index 868edf9665f1..de5820d09d71 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -425,9 +425,11 @@ asmlinkage int compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len,
 				    &kernel_mask);
 	set_fs(old_fs);
 
-	if (ret > 0)
+	if (ret > 0) {
+		ret = sizeof(compat_ulong_t);
 		if (put_user(kernel_mask, user_mask_ptr))
 			return -EFAULT;
+	}
 
 	return ret;
 }
diff --git a/kernel/extable.c b/kernel/extable.c
index d49099854024..6f1fb8c6b75b 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -17,10 +17,10 @@
 */
 #include <linux/module.h>
 #include <asm/uaccess.h>
+#include <asm/sections.h>
 
 extern const struct exception_table_entry __start___ex_table[];
 extern const struct exception_table_entry __stop___ex_table[];
-extern char _stext[], _etext[], _sinittext[], _einittext[];
 
 /* Given an address, look for it in the exception tables. */
 const struct exception_table_entry *search_exception_tables(unsigned long addr)
diff --git a/kernel/fork.c b/kernel/fork.c
index 2928684629e4..7c4c94b1a968 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -53,13 +53,6 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0;
 
 rwlock_t tasklist_lock __cacheline_aligned = RW_LOCK_UNLOCKED;  /* outer */
 
-/*
- * A per-CPU task cache - this relies on the fact that
- * the very last portion of sys_exit() is executed with
- * preemption turned off.
- */
-static task_t *task_cache[NR_CPUS] __cacheline_aligned;
-
 int nr_processes(void)
 {
 	int cpu;
@@ -80,26 +73,8 @@ static kmem_cache_t *task_struct_cachep;
 
 static void free_task(struct task_struct *tsk)
 {
-	/*
-	 * The task cache is effectively disabled right now.
-	 * Do we want it? The slab cache already has per-cpu
-	 * stuff, but the thread info (usually a order-1 page
-	 * allocation) doesn't.
-	 */
-	if (tsk != current) {
-		free_thread_info(tsk->thread_info);
-		free_task_struct(tsk);
-	} else {
-		int cpu = get_cpu();
-
-		tsk = task_cache[cpu];
-		if (tsk) {
-			free_thread_info(tsk->thread_info);
-			free_task_struct(tsk);
-		}
-		task_cache[cpu] = current;
-		put_cpu();
-	}
+	free_thread_info(tsk->thread_info);
+	free_task_struct(tsk);
 }
 
 void __put_task_struct(struct task_struct *tsk)
@@ -220,25 +195,18 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 {
 	struct task_struct *tsk;
 	struct thread_info *ti;
-	int cpu = get_cpu();
 
 	prepare_to_copy(orig);
 
-	tsk = task_cache[cpu];
-	task_cache[cpu] = NULL;
-	put_cpu();
-	if (!tsk) {
-		tsk = alloc_task_struct();
-		if (!tsk)
-			return NULL;
-
-		ti = alloc_thread_info(tsk);
-		if (!ti) {
-			free_task_struct(tsk);
-			return NULL;
-		}
-	} else
-		ti = tsk->thread_info;
+	tsk = alloc_task_struct();
+	if (!tsk)
+		return NULL;
+
+	ti = alloc_thread_info(tsk);
+	if (!ti) {
+		free_task_struct(tsk);
+		return NULL;
+	}
 
 	*ti = *orig->thread_info;
 	*tsk = *orig;
@@ -791,8 +759,10 @@ struct task_struct *copy_process(unsigned long clone_flags,
 		goto fork_out;
 
 	retval = -EAGAIN;
-	if (atomic_read(&p->user->processes) >= p->rlim[RLIMIT_NPROC].rlim_cur) {
-		if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE))
+	if (atomic_read(&p->user->processes) >=
+			p->rlim[RLIMIT_NPROC].rlim_cur) {
+		if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) &&
+				p->user != &root_user)
 			goto bad_fork_free;
 	}
 
@@ -1106,7 +1076,7 @@ long do_fork(unsigned long clone_flags,
 			init_completion(&vfork);
 		}
 
-		if (p->ptrace & PT_PTRACED) {
+		if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) {
 			/*
 			 * We'll start up with an immediate SIGSTOP.
 			 */
@@ -1114,7 +1084,9 @@ long do_fork(unsigned long clone_flags,
 			set_tsk_thread_flag(p, TIF_SIGPENDING);
 		}
 
-		wake_up_forked_process(p);		/* do this last */
+		p->state = TASK_STOPPED;
+		if (!(clone_flags & CLONE_STOPPED))
+			wake_up_forked_process(p);	/* do this last */
 		++total_forks;
 
 		if (unlikely (trace)) {
diff --git a/kernel/module.c b/kernel/module.c
index ea1cf83ee2b3..58d73701bbde 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -98,6 +98,17 @@ int init_module(void)
 }
 EXPORT_SYMBOL(init_module);
 
+/* A thread that wants to hold a reference to a module only while it
+ * is running can call ths to safely exit.
+ * nfsd and lockd use this.
+ */
+void __module_put_and_exit(struct module *mod, long code)
+{
+	module_put(mod);
+	do_exit(code);
+}
+EXPORT_SYMBOL(__module_put_and_exit);
+	
 /* Find a module section: 0 means not found. */
 static unsigned int find_sec(Elf_Ehdr *hdr,
 			     Elf_Shdr *sechdrs,
@@ -374,9 +385,9 @@ static void module_unload_init(struct module *mod)
 
 	INIT_LIST_HEAD(&mod->modules_which_use_me);
 	for (i = 0; i < NR_CPUS; i++)
-		atomic_set(&mod->ref[i].count, 0);
+		local_set(&mod->ref[i].count, 0);
 	/* Hold reference count during initialization. */
-	atomic_set(&mod->ref[smp_processor_id()].count, 1);
+	local_set(&mod->ref[smp_processor_id()].count, 1);
 	/* Backwards compatibility macros put refcount during init. */
 	mod->waiter = current;
 }
@@ -599,7 +610,7 @@ unsigned int module_refcount(struct module *mod)
 	unsigned int i, total = 0;
 
 	for (i = 0; i < NR_CPUS; i++)
-		total += atomic_read(&mod->ref[i].count);
+		total += local_read(&mod->ref[i].count);
 	return total;
 }
 EXPORT_SYMBOL(module_refcount);
@@ -610,7 +621,10 @@ static void free_module(struct module *mod);
 #ifdef CONFIG_MODULE_FORCE_UNLOAD
 static inline int try_force(unsigned int flags)
 {
-	return (flags & O_TRUNC);
+	int ret = (flags & O_TRUNC);
+	if (ret)
+		tainted |= TAINT_FORCED_MODULE;
+	return ret;
 }
 #else
 static inline int try_force(unsigned int flags)
diff --git a/kernel/profile.c b/kernel/profile.c
index 4f6d22ce33f2..5c02ac0fbbda 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -8,8 +8,7 @@
 #include <linux/bootmem.h>
 #include <linux/notifier.h>
 #include <linux/mm.h>
-
-extern char _stext, _etext;
+#include <asm/sections.h>
 
 unsigned int * prof_buffer;
 unsigned long prof_len;
@@ -36,7 +35,7 @@ void __init profile_init(void)
 		return;
  
 	/* only text is profiled */
-	prof_len = (unsigned long) &_etext - (unsigned long) &_stext;
+	prof_len = _etext - _stext;
 	prof_len >>= prof_shift;
 		
 	size = prof_len * sizeof(unsigned int) + PAGE_SIZE - 1;
diff --git a/kernel/sched.c b/kernel/sched.c
index ba4897671015..21ee4d138388 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1151,6 +1151,8 @@ static inline void rebalance_tick(runqueue_t *this_rq, int idle)
 
 DEFINE_PER_CPU(struct kernel_stat, kstat) = { { 0 } };
 
+EXPORT_PER_CPU_SYMBOL(kstat);
+
 /*
  * We place interactive tasks back into the active array, if possible.
  *
@@ -2080,7 +2082,7 @@ asmlinkage long sys_sched_get_priority_max(int policy)
 }
 
 /**
- * sys_sched_get_priority_mix - return minimum RT priority.
+ * sys_sched_get_priority_min - return minimum RT priority.
  * @policy: scheduling class.
  *
  * this syscall returns the minimum rt_priority that can be used
@@ -2541,7 +2543,7 @@ void __might_sleep(char *file, int line)
 		if (time_before(jiffies, prev_jiffy + HZ))
 			return;
 		prev_jiffy = jiffies;
-		printk(KERN_ERR "Debug: sleeping function called from illegal"
+		printk(KERN_ERR "Debug: sleeping function called from invalid"
 				" context at %s:%d\n", file, line);
 		dump_stack();
 	}
diff --git a/kernel/sys.c b/kernel/sys.c
index 4c3f48c93148..0bd0c5a399a6 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -601,6 +601,14 @@ static int set_user(uid_t new_ruid, int dumpclear)
 	new_user = alloc_uid(new_ruid);
 	if (!new_user)
 		return -EAGAIN;
+
+	if (atomic_read(&new_user->processes) >=
+				current->rlim[RLIMIT_NPROC].rlim_cur &&
+			new_user != &root_user) {
+		free_uid(new_user);
+		return -EAGAIN;
+	}
+
 	switch_uid(new_user);
 
 	if(dumpclear)
@@ -1159,6 +1167,7 @@ asmlinkage long sys_newuname(struct new_utsname __user * name)
 asmlinkage long sys_sethostname(char __user *name, int len)
 {
 	int errno;
+	char tmp[__NEW_UTS_LEN];
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -1166,7 +1175,8 @@ asmlinkage long sys_sethostname(char __user *name, int len)
 		return -EINVAL;
 	down_write(&uts_sem);
 	errno = -EFAULT;
-	if (!copy_from_user(system_utsname.nodename, name, len)) {
+	if (!copy_from_user(tmp, name, len)) {
+		memcpy(system_utsname.nodename, tmp, len);
 		system_utsname.nodename[len] = 0;
 		errno = 0;
 	}
@@ -1198,6 +1208,7 @@ asmlinkage long sys_gethostname(char __user *name, int len)
 asmlinkage long sys_setdomainname(char __user *name, int len)
 {
 	int errno;
+	char tmp[__NEW_UTS_LEN];
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -1206,9 +1217,10 @@ asmlinkage long sys_setdomainname(char __user *name, int len)
 
 	down_write(&uts_sem);
 	errno = -EFAULT;
-	if (!copy_from_user(system_utsname.domainname, name, len)) {
-		errno = 0;
+	if (!copy_from_user(tmp, name, len)) {
+		memcpy(system_utsname.domainname, tmp, len);
 		system_utsname.domainname[len] = 0;
+		errno = 0;
 	}
 	up_write(&uts_sem);
 	return errno;
diff --git a/kernel/time.c b/kernel/time.c
index beb7b007b443..fd23f6774b56 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -66,7 +66,7 @@ asmlinkage long sys_time(int * tloc)
  * architectures that need it).
  */
  
-asmlinkage long sys_stime(int * tptr)
+asmlinkage long sys_stime(time_t *tptr)
 {
 	struct timespec tv;
 
@@ -160,22 +160,25 @@ int do_sys_settimeofday(struct timespec *tv, struct timezone *tz)
 	return 0;
 }
 
-asmlinkage long sys_settimeofday(struct timeval __user *tv, struct timezone __user *tz)
+asmlinkage long sys_settimeofday(struct timeval __user *tv,
+				struct timezone __user *tz)
 {
-	struct timespec	new_tv;
+	struct timeval user_tv;
+	struct timespec	new_ts;
 	struct timezone new_tz;
 
 	if (tv) {
-		if (copy_from_user(&new_tv, tv, sizeof(*tv)))
+		if (copy_from_user(&user_tv, tv, sizeof(*tv)))
 			return -EFAULT;
-		new_tv.tv_nsec *= NSEC_PER_USEC;
+		new_ts.tv_sec = user_tv.tv_sec;
+		new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC;
 	}
 	if (tz) {
 		if (copy_from_user(&new_tz, tz, sizeof(*tz)))
 			return -EFAULT;
 	}
 
-	return do_sys_settimeofday(tv ? &new_tv : NULL, tz ? &new_tz : NULL);
+	return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
 }
 
 long pps_offset;		/* pps time offset (us) */