Merge branch 'linus' into sched/core

Merge reason: merge the latest fixes, update to -rc4.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

59 files changed, 309 insertions, 193 deletions

diff --git a/kernel/async.c b/kernel/async.c
index 27235f5de19..15319d6c18f 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -56,6 +56,7 @@ asynchronous and synchronous parts of the kernel.
 #include <linux/init.h>
 #include <linux/kthread.h>
 #include <linux/delay.h>
+#include <linux/slab.h>
 #include <asm/atomic.h>
 
 static async_cookie_t next_cookie = 1;
diff --git a/kernel/audit.c b/kernel/audit.c
index 78f7f86aa23..c71bd26631a 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -46,6 +46,7 @@
 #include <asm/atomic.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/kthread.h>
 
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index 028e85663f2..46a57b57a33 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -3,6 +3,7 @@
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/kthread.h>
+#include <linux/slab.h>
 
 struct audit_tree;
 struct audit_chunk;
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index cc7e87936cb..8df43696f4b 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -27,6 +27,7 @@
 #include <linux/namei.h>
 #include <linux/netlink.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/inotify.h>
 #include <linux/security.h>
 #include "audit.h"
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index a70604047f3..ce08041f578 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -27,6 +27,7 @@
 #include <linux/namei.h>
 #include <linux/netlink.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/security.h>
 #include "audit.h"
 
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index f3a461c0970..3828ad5fb8f 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -49,6 +49,7 @@
 #include <linux/namei.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/mount.h>
 #include <linux/socket.h>
 #include <linux/mqueue.h>
@@ -1893,7 +1894,7 @@ static int audit_inc_name_count(struct audit_context *context,
 {
 	if (context->name_count >= AUDIT_NAMES) {
 		if (inode)
-			printk(KERN_DEBUG "name_count maxed, losing inode data: "
+			printk(KERN_DEBUG "audit: name_count maxed, losing inode data: "
 			       "dev=%02x:%02x, inode=%lu\n",
 			       MAJOR(inode->i_sb->s_dev),
 			       MINOR(inode->i_sb->s_dev),
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index 59e9ef6aab4..da5e1397553 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -15,6 +15,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/cgroup.h>
 #include <linux/fs.h>
 #include <linux/uaccess.h>
@@ -47,17 +48,20 @@ static inline struct freezer *task_freezer(struct task_struct *task)
 			    struct freezer, css);
 }
 
-int cgroup_frozen(struct task_struct *task)
+int cgroup_freezing_or_frozen(struct task_struct *task)
 {
 	struct freezer *freezer;
 	enum freezer_state state;
 
 	task_lock(task);
 	freezer = task_freezer(task);
-	state = freezer->state;
+	if (!freezer->css.cgroup->parent)
+		state = CGROUP_THAWED; /* root cgroup can't be frozen */
+	else
+		state = freezer->state;
 	task_unlock(task);
 
-	return state == CGROUP_FROZEN;
+	return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN);
 }
 
 /*
diff --git a/kernel/compat.c b/kernel/compat.c
index f6c204f07ea..7f40e9275fd 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -25,6 +25,7 @@
 #include <linux/posix-timers.h>
 #include <linux/times.h>
 #include <linux/ptrace.h>
+#include <linux/gfp.h>
 
 #include <asm/uaccess.h>
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 8d340faac38..914aedcde84 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -14,6 +14,7 @@
 #include <linux/kthread.h>
 #include <linux/stop_machine.h>
 #include <linux/mutex.h>
+#include <linux/gfp.h>
 
 #ifdef CONFIG_SMP
 /* Serializes the updates to cpu_online_mask, cpu_present_mask */
diff --git a/kernel/cred.c b/kernel/cred.c
index 19d3ccce3d4..4f483be5944 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -10,6 +10,7 @@
  */
 #include <linux/module.h>
 #include <linux/cred.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/key.h>
 #include <linux/keyctl.h>
diff --git a/kernel/exit.c b/kernel/exit.c
index 84dc4b294e4..eabca5a73a8 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -952,7 +952,8 @@ NORET_TYPE void do_exit(long code)
 
 	acct_update_integrals(tsk);
 	/* sync mm's RSS info before statistics gathering */
-	sync_mm_rss(tsk, tsk->mm);
+	if (tsk->mm)
+		sync_mm_rss(tsk, tsk->mm);
 	group_dead = atomic_dec_and_test(&tsk->signal->live);
 	if (group_dead) {
 		hrtimer_cancel(&tsk->signal->real_timer);
diff --git a/kernel/fork.c b/kernel/fork.c
index 4799c5f0e6d..44b0791b0a2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1052,6 +1052,9 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->prev_utime = cputime_zero;
 	p->prev_stime = cputime_zero;
 #endif
+#if defined(SPLIT_RSS_COUNTING)
+	memset(&p->rss_stat, 0, sizeof(p->rss_stat));
+#endif
 
 	p->default_timer_slack_ns = current->timer_slack_ns;
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 398fda155f6..704e488730a 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -757,6 +757,16 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		if (new->flags & IRQF_ONESHOT)
 			desc->status |= IRQ_ONESHOT;
 
+		/*
+		 * Force MSI interrupts to run with interrupts
+		 * disabled. The multi vector cards can cause stack
+		 * overflows due to nested interrupts when enough of
+		 * them are directed to a core and fire at the same
+		 * time.
+		 */
+		if (desc->msi_desc)
+			new->flags |= IRQF_DISABLED;
+
 		if (!(desc->status & IRQ_NOAUTOEN)) {
 			desc->depth = 0;
 			desc->status &= ~IRQ_DISABLED;
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
index 963559dbd85..65d3845665a 100644
--- a/kernel/irq/numa_migrate.c
+++ b/kernel/irq/numa_migrate.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/irq.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/interrupt.h>
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 6f50eccc79c..7a6eb04ef6b 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/irq.h>
+#include <linux/gfp.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 8e5288a8a35..13aff293f4d 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -21,6 +21,7 @@
 #include <linux/sched.h>	/* for cond_resched */
 #include <linux/mm.h>
 #include <linux/ctype.h>
+#include <linux/slab.h>
 
 #include <asm/sections.h>
 
diff --git a/kernel/kgdb.c b/kernel/kgdb.c
index 761fdd2b303..11f3515ca83 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -69,9 +69,16 @@ struct kgdb_state {
 	struct pt_regs		*linux_regs;
 };
 
+/* Exception state values */
+#define DCPU_WANT_MASTER 0x1 /* Waiting to become a master kgdb cpu */
+#define DCPU_NEXT_MASTER 0x2 /* Transition from one master cpu to another */
+#define DCPU_IS_SLAVE    0x4 /* Slave cpu enter exception */
+#define DCPU_SSTEP       0x8 /* CPU is single stepping */
+
 static struct debuggerinfo_struct {
 	void			*debuggerinfo;
 	struct task_struct	*task;
+	int 			exception_state;
 } kgdb_info[NR_CPUS];
 
 /**
@@ -391,27 +398,22 @@ int kgdb_mem2hex(char *mem, char *buf, int count)
 
 /*
  * Copy the binary array pointed to by buf into mem.  Fix $, #, and
- * 0x7d escaped with 0x7d.  Return a pointer to the character after
- * the last byte written.
+ * 0x7d escaped with 0x7d. Return -EFAULT on failure or 0 on success.
+ * The input buf is overwitten with the result to write to mem.
  */
 static int kgdb_ebin2mem(char *buf, char *mem, int count)
 {
-	int err = 0;
-	char c;
+	int size = 0;
+	char *c = buf;
 
 	while (count-- > 0) {
-		c = *buf++;
-		if (c == 0x7d)
-			c = *buf++ ^ 0x20;
-
-		err = probe_kernel_write(mem, &c, 1);
-		if (err)
-			break;
-
-		mem++;
+		c[size] = *buf++;
+		if (c[size] == 0x7d)
+			c[size] = *buf++ ^ 0x20;
+		size++;
 	}
 
-	return err;
+	return probe_kernel_write(mem, c, size);
 }
 
 /*
@@ -563,49 +565,6 @@ static struct task_struct *getthread(struct pt_regs *regs, int tid)
 }
 
 /*
- * CPU debug state control:
- */
-
-#ifdef CONFIG_SMP
-static void kgdb_wait(struct pt_regs *regs)
-{
-	unsigned long flags;
-	int cpu;
-
-	local_irq_save(flags);
-	cpu = raw_smp_processor_id();
-	kgdb_info[cpu].debuggerinfo = regs;
-	kgdb_info[cpu].task = current;
-	/*
-	 * Make sure the above info reaches the primary CPU before
-	 * our cpu_in_kgdb[] flag setting does:
-	 */
-	smp_wmb();
-	atomic_set(&cpu_in_kgdb[cpu], 1);
-
-	/* Disable any cpu specific hw breakpoints */
-	kgdb_disable_hw_debug(regs);
-
-	/* Wait till primary CPU is done with debugging */
-	while (atomic_read(&passive_cpu_wait[cpu]))
-		cpu_relax();
-
-	kgdb_info[cpu].debuggerinfo = NULL;
-	kgdb_info[cpu].task = NULL;
-
-	/* fix up hardware debug registers on local cpu */
-	if (arch_kgdb_ops.correct_hw_break)
-		arch_kgdb_ops.correct_hw_break();
-
-	/* Signal the primary CPU that we are done: */
-	atomic_set(&cpu_in_kgdb[cpu], 0);
-	touch_softlockup_watchdog_sync();
-	clocksource_touch_watchdog();
-	local_irq_restore(flags);
-}
-#endif
-
-/*
  * Some architectures need cache flushes when we set/clear a
  * breakpoint:
  */
@@ -1400,34 +1359,13 @@ static int kgdb_reenter_check(struct kgdb_state *ks)
 	return 1;
 }
 
-/*
- * kgdb_handle_exception() - main entry point from a kernel exception
- *
- * Locking hierarchy:
- *	interface locks, if any (begin_session)
- *	kgdb lock (kgdb_active)
- */
-int
-kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
+static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs)
 {
-	struct kgdb_state kgdb_var;
-	struct kgdb_state *ks = &kgdb_var;
 	unsigned long flags;
 	int sstep_tries = 100;
 	int error = 0;
 	int i, cpu;
-
-	ks->cpu			= raw_smp_processor_id();
-	ks->ex_vector		= evector;
-	ks->signo		= signo;
-	ks->ex_vector		= evector;
-	ks->err_code		= ecode;
-	ks->kgdb_usethreadid	= 0;
-	ks->linux_regs		= regs;
-
-	if (kgdb_reenter_check(ks))
-		return 0; /* Ouch, double exception ! */
-
+	int trace_on = 0;
 acquirelock:
 	/*
 	 * Interrupts will be restored by the 'trap return' code, except when
@@ -1435,13 +1373,43 @@ acquirelock:
 	 */
 	local_irq_save(flags);
 
-	cpu = raw_smp_processor_id();
+	cpu = ks->cpu;
+	kgdb_info[cpu].debuggerinfo = regs;
+	kgdb_info[cpu].task = current;
+	/*
+	 * Make sure the above info reaches the primary CPU before
+	 * our cpu_in_kgdb[] flag setting does:
+	 */
+	atomic_inc(&cpu_in_kgdb[cpu]);
 
 	/*
-	 * Acquire the kgdb_active lock:
+	 * CPU will loop if it is a slave or request to become a kgdb
+	 * master cpu and acquire the kgdb_active lock:
 	 */
-	while (atomic_cmpxchg(&kgdb_active, -1, cpu) != -1)
+	while (1) {
+		if (kgdb_info[cpu].exception_state & DCPU_WANT_MASTER) {
+			if (atomic_cmpxchg(&kgdb_active, -1, cpu) == cpu)
+				break;
+		} else if (kgdb_info[cpu].exception_state & DCPU_IS_SLAVE) {
+			if (!atomic_read(&passive_cpu_wait[cpu]))
+				goto return_normal;
+		} else {
+return_normal:
+			/* Return to normal operation by executing any
+			 * hw breakpoint fixup.
+			 */
+			if (arch_kgdb_ops.correct_hw_break)
+				arch_kgdb_ops.correct_hw_break();
+			if (trace_on)
+				tracing_on();
+			atomic_dec(&cpu_in_kgdb[cpu]);
+			touch_softlockup_watchdog_sync();
+			clocksource_touch_watchdog();
+			local_irq_restore(flags);
+			return 0;
+		}
 		cpu_relax();
+	}
 
 	/*
 	 * For single stepping, try to only enter on the processor
@@ -1475,9 +1443,6 @@ acquirelock:
 	if (kgdb_io_ops->pre_exception)
 		kgdb_io_ops->pre_exception();
 
-	kgdb_info[ks->cpu].debuggerinfo = ks->linux_regs;
-	kgdb_info[ks->cpu].task = current;
-
 	kgdb_disable_hw_debug(ks->linux_regs);
 
 	/*
@@ -1486,15 +1451,9 @@ acquirelock:
 	 */
 	if (!kgdb_single_step) {
 		for (i = 0; i < NR_CPUS; i++)
-			atomic_set(&passive_cpu_wait[i], 1);
+			atomic_inc(&passive_cpu_wait[i]);
 	}
 
-	/*
-	 * spin_lock code is good enough as a barrier so we don't
-	 * need one here:
-	 */
-	atomic_set(&cpu_in_kgdb[ks->cpu], 1);
-
 #ifdef CONFIG_SMP
 	/* Signal the other CPUs to enter kgdb_wait() */
 	if ((!kgdb_single_step) && kgdb_do_roundup)
@@ -1518,6 +1477,9 @@ acquirelock:
 	kgdb_single_step = 0;
 	kgdb_contthread = current;
 	exception_level = 0;
+	trace_on = tracing_is_on();
+	if (trace_on)
+		tracing_off();
 
 	/* Talk to debugger with gdbserial protocol */
 	error = gdb_serial_stub(ks);
@@ -1526,13 +1488,11 @@ acquirelock:
 	if (kgdb_io_ops->post_exception)
 		kgdb_io_ops->post_exception();
 
-	kgdb_info[ks->cpu].debuggerinfo = NULL;
-	kgdb_info[ks->cpu].task = NULL;
-	atomic_set(&cpu_in_kgdb[ks->cpu], 0);
+	atomic_dec(&cpu_in_kgdb[ks->cpu]);
 
 	if (!kgdb_single_step) {
 		for (i = NR_CPUS-1; i >= 0; i--)
-			atomic_set(&passive_cpu_wait[i], 0);
+			atomic_dec(&passive_cpu_wait[i]);
 		/*
 		 * Wait till all the CPUs have quit
 		 * from the debugger.
@@ -1551,6 +1511,8 @@ kgdb_restore:
 		else
 			kgdb_sstep_pid = 0;
 	}
+	if (trace_on)
+		tracing_on();
 	/* Free kgdb_active */
 	atomic_set(&kgdb_active, -1);
 	touch_softlockup_watchdog_sync();
@@ -1560,13 +1522,52 @@ kgdb_restore:
 	return error;
 }
 
+/*
+ * kgdb_handle_exception() - main entry point from a kernel exception
+ *
+ * Locking hierarchy:
+ *	interface locks, if any (begin_session)
+ *	kgdb lock (kgdb_active)
+ */
+int
+kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
+{
+	struct kgdb_state kgdb_var;
+	struct kgdb_state *ks = &kgdb_var;
+	int ret;
+
+	ks->cpu			= raw_smp_processor_id();
+	ks->ex_vector		= evector;
+	ks->signo		= signo;
+	ks->ex_vector		= evector;
+	ks->err_code		= ecode;
+	ks->kgdb_usethreadid	= 0;
+	ks->linux_regs		= regs;
+
+	if (kgdb_reenter_check(ks))
+		return 0; /* Ouch, double exception ! */
+	kgdb_info[ks->cpu].exception_state |= DCPU_WANT_MASTER;
+	ret = kgdb_cpu_enter(ks, regs);
+	kgdb_info[ks->cpu].exception_state &= ~DCPU_WANT_MASTER;
+	return ret;
+}
+
 int kgdb_nmicallback(int cpu, void *regs)
 {
 #ifdef CONFIG_SMP
+	struct kgdb_state kgdb_var;
+	struct kgdb_state *ks = &kgdb_var;
+
+	memset(ks, 0, sizeof(struct kgdb_state));
+	ks->cpu			= cpu;
+	ks->linux_regs		= regs;
+
 	if (!atomic_read(&cpu_in_kgdb[cpu]) &&
-			atomic_read(&kgdb_active) != cpu &&
-			atomic_read(&cpu_in_kgdb[atomic_read(&kgdb_active)])) {
-		kgdb_wait((struct pt_regs *)regs);
+	    atomic_read(&kgdb_active) != -1 &&
+	    atomic_read(&kgdb_active) != cpu) {
+		kgdb_info[cpu].exception_state |= DCPU_IS_SLAVE;
+		kgdb_cpu_enter(ks, regs);
+		kgdb_info[cpu].exception_state &= ~DCPU_IS_SLAVE;
 		return 0;
 	}
 #endif
@@ -1742,11 +1743,11 @@ EXPORT_SYMBOL_GPL(kgdb_unregister_io_module);
  */
 void kgdb_breakpoint(void)
 {
-	atomic_set(&kgdb_setting_breakpoint, 1);
+	atomic_inc(&kgdb_setting_breakpoint);
 	wmb(); /* Sync point before breakpoint */
 	arch_kgdb_breakpoint();
 	wmb(); /* Sync point after breakpoint */
-	atomic_set(&kgdb_setting_breakpoint, 0);
+	atomic_dec(&kgdb_setting_breakpoint);
 }
 EXPORT_SYMBOL_GPL(kgdb_breakpoint);
 
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index ca07c5c0c91..877fb306d41 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -56,7 +56,6 @@
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/list.h>
-#include <linux/slab.h>
 #include <linux/stacktrace.h>
 
 static DEFINE_SPINLOCK(latency_lock);
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index c927a549db2..2594e1ce41c 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -43,6 +43,7 @@
 #include <linux/ftrace.h>
 #include <linux/stringify.h>
 #include <linux/bitops.h>
+#include <linux/gfp.h>
 
 #include <asm/sections.h>
 
@@ -582,9 +583,6 @@ static int static_obj(void *obj)
 	unsigned long start = (unsigned long) &_stext,
 		      end   = (unsigned long) &_end,
 		      addr  = (unsigned long) obj;
-#ifdef CONFIG_SMP
-	int i;
-#endif
 
 	/*
 	 * static variable?
@@ -595,24 +593,16 @@ static int static_obj(void *obj)
 	if (arch_is_kernel_data(addr))
 		return 1;
 
-#ifdef CONFIG_SMP
 	/*
-	 * percpu var?
+	 * in-kernel percpu var?
 	 */
-	for_each_possible_cpu(i) {
-		start = (unsigned long) &__per_cpu_start + per_cpu_offset(i);
-		end   = (unsigned long) &__per_cpu_start + PERCPU_ENOUGH_ROOM
-					+ per_cpu_offset(i);
-
-		if ((addr >= start) && (addr < end))
-			return 1;
-	}
-#endif
+	if (is_kernel_percpu_address(addr))
+		return 1;
 
 	/*
-	 * module var?
+	 * module static or percpu var?
 	 */
-	return is_module_address(addr);
+	return is_module_address(addr) || is_module_percpu_address(addr);
 }
 
 /*
diff --git a/kernel/module.c b/kernel/module.c
index c968d3606dc..1016b75b026 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -370,27 +370,33 @@ EXPORT_SYMBOL_GPL(find_module);
 
 #ifdef CONFIG_SMP
 
-static void *percpu_modalloc(unsigned long size, unsigned long align,
-			     const char *name)
+static inline void __percpu *mod_perc