Merge branch 'master' of /home/davem/src/GIT/linux-2.6/

Conflicts:
	lib/Kconfig.debug

56 files changed, 197 insertions, 84 deletions

diff --git a/kernel/async.c b/kernel/async.c
index 27235f5de198..15319d6c18fe 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 78f7f86aa238..c71bd26631a2 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 028e85663f27..46a57b57a335 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 cc7e87936cbc..8df43696f4ba 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 a70604047f3c..ce08041f578d 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 f3a461c0970a..3828ad5fb8f1 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 eb3f34d57419..da5e13975531 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>
diff --git a/kernel/compat.c b/kernel/compat.c
index f6c204f07ea6..7f40e9275fd9 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 f8cced2692b3..25bba73b1be3 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 1b1129d0cce8..e1dbe9eef800 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 cce59cb5ee6a..7f2683a10ac4 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -953,7 +953,8 @@ 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 4799c5f0e6d0..44b0791b0a2e 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 398fda155f6e..704e488730a5 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 963559dbd858..65d3845665ac 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 6f50eccc79c0..7a6eb04ef6b5 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 8e5288a8a355..13aff293f4de 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/latencytop.c b/kernel/latencytop.c
index ca07c5c0c914..877fb306d415 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 c927a549db2c..2594e1ce41cb 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 c968d3606dca..1016b75b026a 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_percpu(struct module *mod)
 {
-	void *ptr;
+	return mod->percpu;
+}
 
+static int percpu_modalloc(struct module *mod,
+			   unsigned long size, unsigned long align)
+{
 	if (align > PAGE_SIZE) {
 		printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
-		       name, align, PAGE_SIZE);
+		       mod->name, align, PAGE_SIZE);
 		align = PAGE_SIZE;
 	}
 
-	ptr = __alloc_reserved_percpu(size, align);
-	if (!ptr)
+	mod->percpu = __alloc_reserved_percpu(size, align);
+	if (!mod->percpu) {
 		printk(KERN_WARNING
 		       "Could not allocate %lu bytes percpu data\n", size);
-	return ptr;
+		return -ENOMEM;
+	}
+	mod->percpu_size = size;
+	return 0;
 }
 
-static void percpu_modfree(void *freeme)
+static void percpu_modfree(struct module *mod)
 {
-	free_percpu(freeme);
+	free_percpu(mod->percpu);
 }
 
 static unsigned int find_pcpusec(Elf_Ehdr *hdr,
@@ -400,24 +406,62 @@ static unsigned int find_pcpusec(Elf_Ehdr *hdr,
 	return find_sec(hdr, sechdrs, secstrings, ".data.percpu");
 }
 
-static void percpu_modcopy(void *pcpudest, const void *from, unsigned long size)
+static void percpu_modcopy(struct module *mod,
+			   const void *from, unsigned long size)
 {
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		memcpy(pcpudest + per_cpu_offset(cpu), from, size);
+		memcpy(per_cpu_ptr(mod->percpu, cpu), from, size);
+}
+
+/**
+ * is_module_percpu_address - test whether address is from module static percpu
+ * @addr: address to test
+ *
+ * Test whether @addr belongs to module static percpu area.
+ *
+ * RETURNS:
+ * %true if @addr is from module static percpu area
+ */
+bool is_module_percpu_address(unsigned long addr)
+{
+	struct module *mod;
+	unsigned int cpu;
+
+	preempt_disable();
+
+	list_for_each_entry_rcu(mod, &modules, list) {
+		if (!mod->percpu_size)
+			continue;
+		for_each_possible_cpu(cpu) {
+			void *start = per_cpu_ptr(mod->percpu, cpu);
+
+			if ((void *)addr >= start &&
+			    (void *)addr < start + mod->percpu_size) {
+				preempt_enable();
+				return true;
+			}
+		}
+	}
+
+	preempt_enable();
+	return false;
 }
 
 #else /* ... !CONFIG_SMP */
 
-static inline void *percpu_modalloc(unsigned long size, unsigned long align,
-				    const char *name)
+static inline void __percpu *mod_percpu(struct module *mod)
 {
 	return NULL;
 }
-static inline void percpu_modfree(void *pcpuptr)
+static inline int percpu_modalloc(struct module *mod,
+				  unsigned long size, unsigned long align)
+{
+	return -ENOMEM;
+}
+static inline void percpu_modfree(struct module *mod)
 {
-	BUG();
 }
 static inline unsigned int find_pcpusec(Elf_Ehdr *hdr,
 					Elf_Shdr *sechdrs,
@@ -425,12 +469,16 @@ static inline unsigned int find_pcpusec(Elf_Ehdr *hdr,
 {
 	return 0;
 }
-static inline void percpu_modcopy(void *pcpudst, const void *src,
-				  unsigned long size)
+static inline void percpu_modcopy(struct module *mod,
+				  const void *from, unsigned long size)
 {
 	/* pcpusec should be 0, and size of that section should be 0. */
 	BUG_ON(size != 0);
 }
+bool is_module_percpu_address(unsigned long addr)
+{
+	return false;
+}
 
 #endif /* CONFIG_SMP */
 
@@ -473,11 +521,13 @@ static void module_unload_init(struct module *mod)
 	int cpu;
 
 	INIT_LIST_HEAD(&mod->modules_which_use_me);
-	for_each_possible_cpu(cpu)
-		per_cpu_ptr(mod->refptr, cpu)->count = 0;
+	for_each_possible_cpu(cpu) {
+		per_cpu_ptr(mod->refptr, cpu)->incs = 0;
+		per_cpu_ptr(mod->refptr, cpu)->decs = 0;
+	}
 
 	/* Hold reference count during initialization. */
-	__this_cpu_write(mod->refptr->count, 1);
+	__this_cpu_write(mod->refptr->incs, 1);
 	/* Backwards compatibility macros put refcount during init. */
 	mod->waiter = current;
 }
@@ -616,12 +666,28 @@ static int try_stop_module(struct module *mod, int flags, int *forced)
 
 unsigned int module_refcount(struct module *mod)
 {
-	unsigned int total = 0;
+	unsigned int incs = 0, decs = 0;
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		total += per_cpu_ptr(mod->refptr, cpu)->count;
-	return total;
+		decs += per_cpu_ptr(mod->refptr, cpu)->decs;
+	/*
+	 * ensure the incs are added up after the decs.
+	 * module_put ensures incs are visible before decs with smp_wmb.
+	 *
+	 * This 2-count scheme avoids the situation where the refcount
+	 * for CPU0 is read, then CPU0 increments the module refcount,
+	 * then CPU1 drops that refcount, then the refcount for CPU1 is
+	 * read. We would record a decrement but not its corresponding
+	 * increment so we would see a low count (disaster).
+	 *
+	 * Rare situation? But module_refcount can be preempted, and we
+	 * might be tallying up 4096+ CPUs. So it is not impossible.
+	 */
+	smp_rmb();
+	for_each_possible_cpu(cpu)
+		incs += per_cpu_ptr(mod->refptr, cpu)->incs;
+	return incs - decs;
 }
 EXPORT_SYMBOL(module_refcount);
 
@@ -798,10 +864,11 @@ void module_put(struct module *module)
 {
 	if (module) {
 		preempt_disable();
-		__this_cpu_dec(module->refptr->count);
+		smp_wmb(); /* see comment in module_refcount */
+		__this_cpu_inc(module->refptr->decs);
 
 		trace_module_put(module, _RET_IP_,
-				 __this_cpu_read(module->refptr->count));
+				 __this_cpu_read(module->refptr->decs));
 		/* Maybe they're waiting for us to drop reference? */
 		if (unlikely(!module_is_live(module)))
 			wake_up_process(module->waiter);
@@ -1400,8 +1467,7 @@ static void free_module(struct module *mod)
 	/* This may be NULL, but that's OK */
 	module_free(mod, mod->module_init);
 	kfree(mod->args);
-	if (mod->percpu)
-		percpu_modfree(mod->percpu);
+	percpu_modfree(mod);
 #if defined(CONFIG_MODULE_UNLOAD)
 	if (mod->refptr)
 		free_percpu(mod->refptr);
@@ -1520,7 +1586,7 @@ static int simplify_symbols(Elf_Shdr *sechdrs,
 		default:
 			/* Divert to percpu allocation if a percpu var. */
 			if (sym[i].st_shndx == pcpuindex)
-				secbase = (unsigned long)mod->percpu;
+				secbase = (unsigned long)mod_percpu(mod);
 			else
 				secbase = sechdrs[sym[i].st_shndx].sh_addr;
 			sym[i].st_value += secbase;
@@ -1954,7 +2020,7 @@ static noinline struct module *load_module(void __user *umod,
 	unsigned int modindex, versindex, infoindex, pcpuindex;
 	struct module *mod;
 	long err = 0;
-	void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
+	void *ptr = NULL; /* Stops spurious gcc warning */
 	unsigned long symoffs, stroffs, *strmap;
 
 	mm_segment_t old_fs;
@@ -2094,15 +2160,11 @@ static noinline struct module *load_module(void __user *umod,
 
 	if (pcpuindex) {
 		/* We have a special allocation for this section. */
-		percpu = percpu_modalloc(sechdrs[pcpuindex].sh_size,
-					 sechdrs[pcpuindex].sh_addralign,
-					 mod->name);
-		if (!percpu) {
-			err = -ENOMEM;
+		err = percpu_modalloc(mod, sechdrs[pcpuindex].sh_size,
+				      sechdrs[pcpuindex].sh_addralign);
+		if (err)
 			goto free_mod;
-		}
 		sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC;
-		mod->percpu = percpu;
 	}
 
 	/* Determine total sizes, and put offsets in sh_entsize.  For now
@@ -2317,7 +2379,7 @@ static noinline struct module *load_module(void __user *umod,
 	sort_extable(mod->extable, mod->extable + mod->num_exentries);
 
 	/* Finally, copy percpu area over. */
-	percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr,
+	percpu_modcopy(mod, (void *)sechdrs[pcpuindex].sh_addr,
 		       sechdrs[pcpuindex].sh_size);
 
 	add_kallsyms(mod, sechdrs, hdr->e_shnum, symindex, strindex,
@@ -2409,8 +2471,7 @@ static noinline struct module *load_module(void __user *umod,
 	module_free(mod, mod->module_core);
 	/* mod will be freed with core. Don't access it beyond this line! */
  free_percpu:
-	if (percpu)
-		percpu_modfree(percpu);
+	percpu_modfree(mod);
  free_mod:
 	kfree(args);
 	kfree(strmap);
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 2ab67233ee8f..f74e6c00e26d 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -13,6 +13,7 @@
  *             Pavel Emelianov <xemul@openvz.org>
  */
 
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/nsproxy.h>
 #include <linux/init_task.h>
diff --git a/kernel/padata.c b/kernel/padata.c
index 93caf65ff57c..fd03513c7327 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -25,6 +25,7 @@
 #include <linux/padata.h>
 #include <linux/mutex.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/rcupdate.h>
 
 #define MAX_SEQ_NR INT_MAX - NR_CPUS
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 574ee58a3046..2f3fbf84215a 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -15,6 +15,7 @@
 #include <linux/smp.h>
 #include <linux/file.h>
 #include <linux/poll.h>
+#include <linux/slab.h>
 #include <linux/sysfs.h>
 #include <linux/dcache.h>
 #include <linux/percpu.h>
@@ -1164,11 +1165,9 @@ void perf_event_task_sched_out(struct task_struct *task,
 	struct perf_event_context *ctx = task->perf_event_ctxp;
 	struct perf_event_context *next_ctx;
 	struct perf_event_context *parent;
-	struct pt_regs *regs;
 	int do_switch = 1;
 
-	regs = task_pt_regs(task);
-	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, regs, 0);
+	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
 
 	if (likely(!ctx || !cpuctx->task_ctx))
 		return;
@@ -2786,12 +2785,11 @@ __weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return NULL;
 }
 
-#ifdef CONFIG_EVENT_TRACING
 __weak
 void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
 {
 }
-#endif
+
 
 /*
  * Output
@@ -3378,15 +3376,23 @@ static void perf_event_task_output(struct perf_event *event,
 				     struct perf_task_event *task_event)
 {
 	struct perf_output_handle handle;
-	int size;
 	struct task_struct *task = task_event->task;
-	int ret;
+	unsigned long flags;