2.6.37.1-stable review

@@ -297,6 +297,12 @@ void __init arm_memblock_init(struct mem
 	memblock_reserve(__pa(_stext), _end - _stext);
 #endif
 #ifdef CONFIG_BLK_DEV_INITRD
+	if (phys_initrd_size &&
+	    memblock_is_region_reserved(phys_initrd_start, phys_initrd_size)) {
+		pr_err("INITRD: 0x%08lx+0x%08lx overlaps in-use memory region - disabling initrd\n",
+		       phys_initrd_start, phys_initrd_size);
+		phys_initrd_start = phys_initrd_size = 0;
+	}
 	if (phys_initrd_size) {
 		memblock_reserve(phys_initrd_start, phys_initrd_size);
 

@@ -1842,6 +1842,7 @@ static int __mem_cgroup_do_charge(struct
 		if (likely(!ret))
 			return CHARGE_OK;
 
+		res_counter_uncharge(&mem->res, csize);
 		mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw);
 		flags |= MEM_CGROUP_RECLAIM_NOSWAP;
 	} else

@@ -462,7 +462,7 @@ static int __devinit sdh_probe(struct pl
 		goto out;
 	}
 
-	mmc = mmc_alloc_host(sizeof(*mmc), &pdev->dev);
+	mmc = mmc_alloc_host(sizeof(struct sdh_host), &pdev->dev);
 	if (!mmc) {
 		ret = -ENOMEM;
 		goto out;

@@ -1030,7 +1030,6 @@ struct inode *exofs_iget(struct super_bl
 		memcpy(oi->i_data, fcb.i_data, sizeof(fcb.i_data));
 	}
 
-	inode->i_mapping->backing_dev_info = sb->s_bdi;
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &exofs_file_inode_operations;
 		inode->i_fop = &exofs_file_operations;

@@ -1131,7 +1130,6 @@ struct inode *exofs_new_inode(struct ino
 
 	sbi = sb->s_fs_info;
 
-	inode->i_mapping->backing_dev_info = sb->s_bdi;
 	sb->s_dirt = 1;
 	inode_init_owner(inode, dir, mode);
 	inode->i_ino = sbi->s_nextid++;

@@ -3821,7 +3821,7 @@ static ssize_t show_slab_objects(struct
 		}
 	}
 
-	down_read(&slub_lock);
+	lock_memory_hotplug();
 #ifdef CONFIG_SLUB_DEBUG
 	if (flags & SO_ALL) {
 		for_each_node_state(node, N_NORMAL_MEMORY) {

@@ -3862,7 +3862,7 @@ static ssize_t show_slab_objects(struct
 			x += sprintf(buf + x, " N%d=%lu",
 					node, nodes[node]);
 #endif
-	up_read(&slub_lock);
+	unlock_memory_hotplug();
 	kfree(nodes);
 	return x + sprintf(buf + x, "\n");
 }

@@ -1392,7 +1392,7 @@ static int ax25_getname(struct socket *s
 	ax25_cb *ax25;
 	int err = 0;
 
-	memset(fsa, 0, sizeof(fsa));
+	memset(fsa, 0, sizeof(*fsa));
 	lock_sock(sk);
 	ax25 = ax25_sk(sk);
 

@@ -105,7 +105,7 @@ static int __devinit platform_pci_init(s
 				       const struct pci_device_id *ent)
 {
 	int i, ret;
-	long ioaddr, iolen;
+	long ioaddr;
 	long mmio_addr, mmio_len;
 	unsigned int max_nr_gframes;
 

@@ -114,7 +114,6 @@ static int __devinit platform_pci_init(s
 		return i;
 
 	ioaddr = pci_resource_start(pdev, 0);
-	iolen = pci_resource_len(pdev, 0);
 
 	mmio_addr = pci_resource_start(pdev, 1);
 	mmio_len = pci_resource_len(pdev, 1);

@@ -125,19 +124,13 @@ static int __devinit platform_pci_init(s
 		goto pci_out;
 	}
 
-	if (request_mem_region(mmio_addr, mmio_len, DRV_NAME) == NULL) {
-		dev_err(&pdev->dev, "MEM I/O resource 0x%lx @ 0x%lx busy\n",
-		       mmio_addr, mmio_len);
-		ret = -EBUSY;
+	ret = pci_request_region(pdev, 1, DRV_NAME);
+	if (ret < 0)
 		goto pci_out;
-	}
 
-	if (request_region(ioaddr, iolen, DRV_NAME) == NULL) {
-		dev_err(&pdev->dev, "I/O resource 0x%lx @ 0x%lx busy\n",
-		       iolen, ioaddr);
-		ret = -EBUSY;
+	ret = pci_request_region(pdev, 0, DRV_NAME);
+	if (ret < 0)
 		goto mem_out;
-	}
 
 	platform_mmio = mmio_addr;
 	platform_mmiolen = mmio_len;

@@ -169,9 +162,9 @@ static int __devinit platform_pci_init(s
 	return 0;
 
 out:
-	release_region(ioaddr, iolen);
+	pci_release_region(pdev, 0);
 mem_out:
-	release_mem_region(mmio_addr, mmio_len);
+	pci_release_region(pdev, 1);
 pci_out:
 	pci_disable_device(pdev);
 	return ret;

@@ -458,12 +458,6 @@ static inline int zone_is_oom_locked(con
 	return test_bit(ZONE_OOM_LOCKED, &zone->flags);
 }
 
-#ifdef CONFIG_SMP
-unsigned long zone_nr_free_pages(struct zone *zone);
-#else
-#define zone_nr_free_pages(zone) zone_page_state(zone, NR_FREE_PAGES)
-#endif /* CONFIG_SMP */
-
 /*
  * The "priority" of VM scanning is how much of the queues we will scan in one
  * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the

@@ -661,7 +655,9 @@ typedef struct pglist_data {
 extern struct mutex zonelists_mutex;
 void build_all_zonelists(void *data);
 void wakeup_kswapd(struct zone *zone, int order);
-int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+		int classzone_idx, int alloc_flags);
+bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
 		int classzone_idx, int alloc_flags);
 enum memmap_context {
 	MEMMAP_EARLY,

@@ -254,6 +254,8 @@ extern void dec_zone_state(struct zone *
 extern void __dec_zone_state(struct zone *, enum zone_stat_item);
 
 void refresh_cpu_vm_stats(int);
+void reduce_pgdat_percpu_threshold(pg_data_t *pgdat);
+void restore_pgdat_percpu_threshold(pg_data_t *pgdat);
 #else /* CONFIG_SMP */
 
 /*

@@ -298,6 +300,9 @@ static inline void __dec_zone_page_state
 #define dec_zone_page_state __dec_zone_page_state
 #define mod_zone_page_state __mod_zone_page_state
 
+static inline void reduce_pgdat_percpu_threshold(pg_data_t *pgdat) { }
+static inline void restore_pgdat_percpu_threshold(pg_data_t *pgdat) { }
+
 static inline void refresh_cpu_vm_stats(int cpu) { }
 #endif
 

@@ -87,24 +87,3 @@ int memmap_valid_within(unsigned long pf
 	return 1;
 }
 #endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */
-
-#ifdef CONFIG_SMP
-/* Called when a more accurate view of NR_FREE_PAGES is needed */
-unsigned long zone_nr_free_pages(struct zone *zone)
-{
-	unsigned long nr_free_pages = zone_page_state(zone, NR_FREE_PAGES);
-
-	/*
-	 * While kswapd is awake, it is considered the zone is under some
-	 * memory pressure. Under pressure, there is a risk that
-	 * per-cpu-counter-drift will allow the min watermark to be breached
-	 * potentially causing a live-lock. While kswapd is awake and
-	 * free pages are low, get a better estimate for free pages
-	 */
-	if (nr_free_pages < zone->percpu_drift_mark &&
-			!waitqueue_active(&zone->zone_pgdat->kswapd_wait))
-		return zone_page_state_snapshot(zone, NR_FREE_PAGES);
-
-	return nr_free_pages;
-}
-#endif /* CONFIG_SMP */

@@ -1460,24 +1460,24 @@ static inline int should_fail_alloc_page
 #endif /* CONFIG_FAIL_PAGE_ALLOC */
 
 /*
- * Return 1 if free pages are above 'mark'. This takes into account the order
+ * Return true if free pages are above 'mark'. This takes into account the order
  * of the allocation.
  */
-int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
-		      int classzone_idx, int alloc_flags)
+static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+		      int classzone_idx, int alloc_flags, long free_pages)
 {
 	/* free_pages my go negative - that's OK */
 	long min = mark;
-	long free_pages = zone_nr_free_pages(z) - (1 << order) + 1;
 	int o;
 
+	free_pages -= (1 << order) + 1;
 	if (alloc_flags & ALLOC_HIGH)
 		min -= min / 2;
 	if (alloc_flags & ALLOC_HARDER)
 		min -= min / 4;
 
 	if (free_pages <= min + z->lowmem_reserve[classzone_idx])
-		return 0;
+		return false;
 	for (o = 0; o < order; o++) {
 		/* At the next order, this order's pages become unavailable */
 		free_pages -= z->free_area[o].nr_free << o;

@@ -1486,9 +1486,28 @@ int zone_watermark_ok(struct zone *z, in
 		min >>= 1;
 
 		if (free_pages <= min)
-			return 0;
+			return false;
 	}
-	return 1;
+	return true;
+}
+
+bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+		      int classzone_idx, int alloc_flags)
+{
+	return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
+					zone_page_state(z, NR_FREE_PAGES));
+}
+
+bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
+		      int classzone_idx, int alloc_flags)
+{
+	long free_pages = zone_page_state(z, NR_FREE_PAGES);
+
+	if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
+		free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);
+
+	return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
+								free_pages);
 }
 
 #ifdef CONFIG_NUMA

@@ -2442,7 +2461,7 @@ void show_free_areas(void)
 			" all_unreclaimable? %s"
 			"\n",
 			zone->name,
-			K(zone_nr_free_pages(zone)),
+			K(zone_page_state(zone, NR_FREE_PAGES)),
 			K(min_wmark_pages(zone)),
 			K(low_wmark_pages(zone)),
 			K(high_wmark_pages(zone)),

@@ -2143,7 +2143,7 @@ static int sleeping_prematurely(pg_data_
 		if (zone->all_unreclaimable)
 			continue;
 
-		if (!zone_watermark_ok(zone, order, high_wmark_pages(zone),
+		if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone),
 								0, 0))
 			return 1;
 	}

@@ -2230,7 +2230,7 @@ loop_again:
 				shrink_active_list(SWAP_CLUSTER_MAX, zone,
 							&sc, priority, 0);
 
-			if (!zone_watermark_ok(zone, order,
+			if (!zone_watermark_ok_safe(zone, order,
 					high_wmark_pages(zone), 0, 0)) {
 				end_zone = i;
 				break;

@@ -2276,7 +2276,7 @@ loop_again:
 			 * We put equal pressure on every zone, unless one
 			 * zone has way too many pages free already.
 			 */
-			if (!zone_watermark_ok(zone, order,
+			if (!zone_watermark_ok_safe(zone, order,
 					8*high_wmark_pages(zone), end_zone, 0))
 				shrink_zone(priority, zone, &sc);
 			reclaim_state->reclaimed_slab = 0;

@@ -2297,7 +2297,7 @@ loop_again:
 			    total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
 				sc.may_writepage = 1;
 
-			if (!zone_watermark_ok(zone, order,
+			if (!zone_watermark_ok_safe(zone, order,
 					high_wmark_pages(zone), end_zone, 0)) {
 				all_zones_ok = 0;
 				/*

@@ -2305,7 +2305,7 @@ loop_again:
 				 * means that we have a GFP_ATOMIC allocation
 				 * failure risk. Hurry up!
 				 */
-				if (!zone_watermark_ok(zone, order,
+				if (!zone_watermark_ok_safe(zone, order,
 					    min_wmark_pages(zone), end_zone, 0))
 					has_under_min_watermark_zone = 1;
 			} else {

@@ -2448,7 +2448,9 @@ static int kswapd(void *p)
 				 */
 				if (!sleeping_prematurely(pgdat, order, remaining)) {
 					trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
+					restore_pgdat_percpu_threshold(pgdat);
 					schedule();
+					reduce_pgdat_percpu_threshold(pgdat);
 				} else {
 					if (remaining)
 						count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);

@@ -2487,16 +2489,17 @@ void wakeup_kswapd(struct zone *zone, in
 	if (!populated_zone(zone))
 		return;
 
-	pgdat = zone->zone_pgdat;
-	if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
+	if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 		return;
+	pgdat = zone->zone_pgdat;
 	if (pgdat->kswapd_max_order < order)
 		pgdat->kswapd_max_order = order;
-	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
-	if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
-		return;
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
+	if (zone_watermark_ok_safe(zone, order, low_wmark_pages(zone), 0, 0))
+		return;
+
+	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
 	wake_up_interruptible(&pgdat->kswapd_wait);
 }
 

86 lines not on this page · raw message

@@ -22,7 +22,7 @@ struct klist {
 	struct list_head	k_list;
 	void			(*get)(struct klist_node *);
 	void			(*put)(struct klist_node *);
-} __attribute__ ((aligned (4)));
+} __attribute__ ((aligned (sizeof(void *))));
 
 #define KLIST_INIT(_name, _get, _put)					\
 	{ .k_lock	= __SPIN_LOCK_UNLOCKED(_name.k_lock),		\

@@ -1111,6 +1111,17 @@ static int ep_send_events(struct eventpo
 	return ep_scan_ready_list(ep, ep_send_events_proc, &esed);
 }
 
+static inline struct timespec ep_set_mstimeout(long ms)
+{
+	struct timespec now, ts = {
+		.tv_sec = ms / MSEC_PER_SEC,
+		.tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC),
+	};
+
+	ktime_get_ts(&now);
+	return timespec_add_safe(now, ts);
+}
+
 static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		   int maxevents, long timeout)
 {

@@ -1118,12 +1129,11 @@ static int ep_poll(struct eventpoll *ep,
 	unsigned long flags;
 	long slack;
 	wait_queue_t wait;
-	struct timespec end_time;
 	ktime_t expires, *to = NULL;
 
 	if (timeout > 0) {
-		ktime_get_ts(&end_time);
-		timespec_add_ns(&end_time, (u64)timeout * NSEC_PER_MSEC);
+		struct timespec end_time = ep_set_mstimeout(timeout);
+
 		slack = select_estimate_accuracy(&end_time);
 		to = &expires;
 		*to = timespec_to_ktime(end_time);

@@ -81,10 +81,10 @@ extern int wait_for_completion_interrupt
 extern int wait_for_completion_killable(struct completion *x);
 extern unsigned long wait_for_completion_timeout(struct completion *x,
 						   unsigned long timeout);
-extern unsigned long wait_for_completion_interruptible_timeout(
-			struct completion *x, unsigned long timeout);
-extern unsigned long wait_for_completion_killable_timeout(
-			struct completion *x, unsigned long timeout);
+extern long wait_for_completion_interruptible_timeout(
+	struct completion *x, unsigned long timeout);
+extern long wait_for_completion_killable_timeout(
+	struct completion *x, unsigned long timeout);
 extern bool try_wait_for_completion(struct completion *x);
 extern bool completion_done(struct completion *x);
 

@@ -4526,7 +4526,7 @@ EXPORT_SYMBOL(wait_for_completion_interr
  * This waits for either a completion of a specific task to be signaled or for a
  * specified timeout to expire. It is interruptible. The timeout is in jiffies.
  */
-unsigned long __sched
+long __sched
 wait_for_completion_interruptible_timeout(struct completion *x,
 					  unsigned long timeout)
 {

@@ -4559,7 +4559,7 @@ EXPORT_SYMBOL(wait_for_completion_killab
  * signaled or for a specified timeout to expire. It can be
  * interrupted by a kill signal. The timeout is in jiffies.
  */
-unsigned long __sched
+long __sched
 wait_for_completion_killable_timeout(struct completion *x,
 				     unsigned long timeout)
 {

@@ -607,6 +607,9 @@ static inline struct task_group *task_gr
 {
 	struct cgroup_subsys_state *css;
 
+	if (p->flags & PF_EXITING)
+		return &root_task_group;
+
 	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
 			lockdep_is_held(&task_rq(p)->lock));
 	return container_of(css, struct task_group, css);

@@ -9178,6 +9181,20 @@ cpu_cgroup_attach(struct cgroup_subsys *
 	}
 }
 
+static void
+cpu_cgroup_exit(struct cgroup_subsys *ss, struct task_struct *task)
+{
+	/*
+	 * cgroup_exit() is called in the copy_process() failure path.
+	 * Ignore this case since the task hasn't ran yet, this avoids
+	 * trying to poke a half freed task state from generic code.
+	 */
+	if (!(task->flags & PF_EXITING))
+		return;
+
+	sched_move_task(task);
+}
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype,
 				u64 shareval)

@@ -9250,6 +9267,7 @@ struct cgroup_subsys cpu_cgroup_subsys =
 	.destroy	= cpu_cgroup_destroy,
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
+	.exit		= cpu_cgroup_exit,
 	.populate	= cpu_cgroup_populate,
 	.subsys_id	= cpu_cgroup_subsys_id,
 	.early_init	= 1,

@@ -606,7 +606,7 @@ static void update_curr_rt(struct rq *rq
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 	u64 delta_exec;
 
-	if (!task_has_rt_policy(curr))
+	if (curr->sched_class != &rt_sched_class)
 		return;
 
 	delta_exec = rq->clock_task - curr->se.exec_start;

@@ -3412,6 +3412,10 @@ static bool cfq_should_wait_busy(struct
 {
 	struct cfq_io_context *cic = cfqd->active_cic;
 
+	/* If the queue already has requests, don't wait */
+	if (!RB_EMPTY_ROOT(&cfqq->sort_list))
+		return false;
+
 	/* If there are other queues in the group, don't wait */
 	if (cfqq->cfqg->nr_cfqq > 1)
 		return false;

@@ -701,6 +701,13 @@ EXPORT_SYMBOL(arch_free_page);
 /* NB: reg/unreg are called while guarded with the tracepoints_mutex */
 extern long hcall_tracepoint_refcount;
 
+/*
+ * Since the tracing code might execute hcalls we need to guard against
+ * recursion. One example of this are spinlocks calling H_YIELD on
+ * shared processor partitions.
+ */
+static DEFINE_PER_CPU(unsigned int, hcall_trace_depth);
+
 void hcall_tracepoint_regfunc(void)
 {
 	hcall_tracepoint_refcount++;

@@ -713,12 +720,42 @@ void hcall_tracepoint_unregfunc(void)
 
 void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
 {
+	unsigned long flags;
+	unsigned int *depth;
+
+	local_irq_save(flags);
+
+	depth = &__get_cpu_var(hcall_trace_depth);
+
+	if (*depth)
+		goto out;
+
+	(*depth)++;
 	trace_hcall_entry(opcode, args);
+	(*depth)--;
+
+out:
+	local_irq_restore(flags);
 }
 
 void __trace_hcall_exit(long opcode, unsigned long retval,
 			unsigned long *retbuf)
 {
+	unsigned long flags;
+	unsigned int *depth;
+
+	local_irq_save(flags);
+
+	depth = &__get_cpu_var(hcall_trace_depth);
+
+	if (*depth)
+		goto out;
+
+	(*depth)++;
 	trace_hcall_exit(opcode, retval, retbuf);
+	(*depth)--;
+
+out:
+	local_irq_restore(flags);
 }
 #endif

@@ -181,7 +181,7 @@ static void unmap_cpu_from_node(unsigned
 	dbg("removing cpu %lu from node %d\n", cpu, node);
 
 	if (cpumask_test_cpu(cpu, node_to_cpumask_map[node])) {
-		cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
+		cpumask_clear_cpu(cpu, node_to_cpumask_map[node]);
 	} else {
 		printk(KERN_ERR "WARNING: cpu %lu not found in node %d\n",
 		       cpu, node);

@@ -2375,6 +2375,7 @@ static int gsmld_config(struct tty_struc
 
 	gsm->initiator = c->initiator;
 	gsm->mru = c->mru;
+	gsm->mtu = c->mtu;
 	gsm->encoding = c->encapsulation;
 	gsm->adaption = c->adaption;
 	gsm->n2 = c->n2;

@@ -75,6 +75,8 @@ static size_t config_rom_length = 1 + 4
 #define BIB_IRMC		((1) << 31)
 #define NODE_CAPABILITIES	0x0c0083c0 /* per IEEE 1394 clause 8.3.2.6.5.2 */
 
+#define CANON_OUI		0x000085
+
 static void generate_config_rom(struct fw_card *card, __be32 *config_rom)
 {
 	struct fw_descriptor *desc;

@@ -284,6 +286,7 @@ static void bm_work(struct work_struct *
 	bool root_device_is_running;
 	bool root_device_is_cmc;
 	bool irm_is_1394_1995_only;
+	bool keep_this_irm;
 
 	spin_lock_irq(&card->lock);
 

@@ -305,6 +308,10 @@ static void bm_work(struct work_struct *
 	irm_is_1394_1995_only = irm_device && irm_device->config_rom &&
 			(irm_device->config_rom[2] & 0x000000f0) == 0;
 
+	/* Canon MV5i works unreliably if it is not root node. */
+	keep_this_irm = irm_device && irm_device->config_rom &&
+			irm_device->config_rom[3] >> 8 == CANON_OUI;
+
 	root_id  = root_node->node_id;
 	irm_id   = card->irm_node->node_id;
 	local_id = card->local_node->node_id;

@@ -333,7 +340,7 @@ static void bm_work(struct work_struct *
 			goto pick_me;
 		}
 
-		if (irm_is_1394_1995_only) {
+		if (irm_is_1394_1995_only && !keep_this_irm) {
 			new_root_id = local_id;
 			fw_notify("%s, making local node (%02x) root.\n",
 				  "IRM is not 1394a compliant", new_root_id);

@@ -382,7 +389,7 @@ static void bm_work(struct work_struct *
 
 		spin_lock_irq(&card->lock);
 
-		if (rcode != RCODE_COMPLETE) {
+		if (rcode != RCODE_COMPLETE && !keep_this_irm) {
 			/*
 			 * The lock request failed, maybe the IRM
 			 * isn't really IRM capable after all. Let's

@@ -522,12 +522,15 @@ static inline void print_irqtrace_events
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # ifdef CONFIG_PROVE_LOCKING
 #  define lock_map_acquire(l)		lock_acquire(l, 0, 0, 0, 2, NULL, _THIS_IP_)
+#  define lock_map_acquire_read(l)	lock_acquire(l, 0, 0, 2, 2, NULL, _THIS_IP_)
 # else
 #  define lock_map_acquire(l)		lock_acquire(l, 0, 0, 0, 1, NULL, _THIS_IP_)
+#  define lock_map_acquire_read(l)	lock_acquire(l, 0, 0, 2, 1, NULL, _THIS_IP_)
 # endif
 # define lock_map_release(l)			lock_release(l, 1, _THIS_IP_)
 #else
 # define lock_map_acquire(l)			do { } while (0)
+# define lock_map_acquire_read(l)		do { } while (0)
 # define lock_map_release(l)			do { } while (0)
 #endif
 

@@ -1806,7 +1806,7 @@ __acquires(&gcwq->lock)
 	spin_unlock_irq(&gcwq->lock);
 
 	work_clear_pending(work);
-	lock_map_acquire(&cwq->wq->lockdep_map);
+	lock_map_acquire_read(&cwq->wq->lockdep_map);
 	lock_map_acquire(&lockdep_map);
 	trace_workqueue_execute_start(work);
 	f(work);

@@ -2350,8 +2350,18 @@ static bool start_flush_work(struct work
 	insert_wq_barrier(cwq, barr, work, worker);
 	spin_unlock_irq(&gcwq->lock);
 
-	lock_map_acquire(&cwq->wq->lockdep_map);
+	/*
+	 * If @max_active is 1 or rescuer is in use, flushing another work
+	 * item on the same workqueue may lead to deadlock.  Make sure the
+	 * flusher is not running on the same workqueue by verifying write
+	 * access.
+	 */
+	if (cwq->wq->saved_max_active == 1 || cwq->wq->flags & WQ_RESCUER)
+		lock_map_acquire(&cwq->wq->lockdep_map);
+	else
+		lock_map_acquire_read(&cwq->wq->lockdep_map);
 	lock_map_release(&cwq->wq->lockdep_map);
+
 	return true;
 already_gone:
 	spin_unlock_irq(&gcwq->lock);

@@ -347,7 +347,7 @@ extern int CIFSSMBLock(const int xid, st
 			const __u16 netfid, const __u64 len,
 			const __u64 offset, const __u32 numUnlock,
 			const __u32 numLock, const __u8 lockType,
-			const bool waitFlag);
+			const bool waitFlag, const __u8 oplock_level);
 extern int CIFSSMBPosixLock(const int xid, struct cifsTconInfo *tcon,
 			const __u16 smb_file_id, const int get_flag,
 			const __u64 len, struct file_lock *,

@@ -1666,7 +1666,8 @@ int
 CIFSSMBLock(const int xid, struct cifsTconInfo *tcon,
 	    const __u16 smb_file_id, const __u64 len,
 	    const __u64 offset, const __u32 numUnlock,
-	    const __u32 numLock, const __u8 lockType, const bool waitFlag)
+	    const __u32 numLock, const __u8 lockType,
+	    const bool waitFlag, const __u8 oplock_level)
 {
 	int rc = 0;
 	LOCK_REQ *pSMB = NULL;

@@ -1694,6 +1695,7 @@ CIFSSMBLock(const int xid, struct cifsTc
 	pSMB->NumberOfLocks = cpu_to_le16(numLock);
 	pSMB->NumberOfUnlocks = cpu_to_le16(numUnlock);
 	pSMB->LockType = lockType;
+	pSMB->OplockLevel = oplock_level;
 	pSMB->AndXCommand = 0xFF;	/* none */
 	pSMB->Fid = smb_file_id; /* netfid stays le */
 

@@ -779,12 +779,12 @@ int cifs_lock(struct file *file, int cmd
 
 		/* BB we could chain these into one lock request BB */
 		rc = CIFSSMBLock(xid, tcon, netfid, length, pfLock->fl_start,
-				 0, 1, lockType, 0 /* wait flag */ );
+				 0, 1, lockType, 0 /* wait flag */, 0);
 		if (rc == 0) {
 			rc = CIFSSMBLock(xid, tcon, netfid, length,
 					 pfLock->fl_start, 1 /* numUnlock */ ,
 					 0 /* numLock */ , lockType,
-					 0 /* wait flag */ );
+					 0 /* wait flag */, 0);
 			pfLock->fl_type = F_UNLCK;
 			if (rc != 0)
 				cERROR(1, "Error unlocking previously locked "

@@ -801,13 +801,13 @@ int cifs_lock(struct file *file, int cmd
 				rc = CIFSSMBLock(xid, tcon, netfid, length,
 					pfLock->fl_start, 0, 1,
 					lockType | LOCKING_ANDX_SHARED_LOCK,
-					0 /* wait flag */);
+					0 /* wait flag */, 0);
 				if (rc == 0) {
 					rc = CIFSSMBLock(xid, tcon, netfid,
 						length, pfLock->fl_start, 1, 0,
 						lockType |
 						LOCKING_ANDX_SHARED_LOCK,
-						0 /* wait flag */);
+						0 /* wait flag */, 0);
 					pfLock->fl_type = F_RDLCK;
 					if (rc != 0)
 						cERROR(1, "Error unlocking "

@@ -850,8 +850,8 @@ int cifs_lock(struct file *file, int cmd
 
 		if (numLock) {
 			rc = CIFSSMBLock(xid, tcon, netfid, length,
-					pfLock->fl_start,
-					0, numLock, lockType, wait_flag);
+					 pfLock->fl_start, 0, numLock, lockType,
+					 wait_flag, 0);
 
 			if (rc == 0) {
 				/* For Windows locks we must store them. */

@@ -871,9 +871,9 @@ int cifs_lock(struct file *file, int cmd
 						(pfLock->fl_start + length) >=
 						(li->offset + li->length)) {
 					stored_rc = CIFSSMBLock(xid, tcon,
-							netfid,
-							li->length, li->offset,
-							1, 0, li->type, false);
+							netfid, li->length,
+							li->offset, 1, 0,
+							li->type, false, 0);
 					if (stored_rc)
 						rc = stored_rc;
 					else {

@@ -2245,7 +2245,8 @@ void cifs_oplock_break(struct work_struc
 	 */
 	if (!cfile->oplock_break_cancelled) {
 		rc = CIFSSMBLock(0, tlink_tcon(cfile->tlink), cfile->netfid, 0,
-				 0, 0, 0, LOCKING_ANDX_OPLOCK_RELEASE, false);
+				 0, 0, 0, LOCKING_ANDX_OPLOCK_RELEASE, false,
+				 cinode->clientCanCacheRead ? 1 : 0);
 		cFYI(1, "Oplock release rc = %d", rc);
 	}
 

@@ -571,7 +571,7 @@ is_valid_oplock_break(struct smb_hdr *bu
 				pCifsInode = CIFS_I(netfile->dentry->d_inode);
 
 				cifs_set_oplock_level(pCifsInode,
-						      pSMB->OplockLevel);
+					pSMB->OplockLevel ? OPLOCK_READ : 0);
 				/*
 				 * cifs_oplock_break_put() can't be called
 				 * from here.  Get reference after queueing

@@ -2999,7 +2999,7 @@ CIFSTCon(unsigned int xid, struct cifsSe
 		bcc_ptr++;              /* skip password */
 		/* already aligned so no need to do it below */
 	} else {
-		pSMB->PasswordLength = cpu_to_le16(CIFS_SESS_KEY_SIZE);
+		pSMB->PasswordLength = cpu_to_le16(CIFS_AUTH_RESP_SIZE);
 		/* BB FIXME add code to fail this if NTLMv2 or Kerberos
 		   specified as required (when that support is added to
 		   the vfs in the future) as only NTLM or the much

@@ -3017,7 +3017,7 @@ CIFSTCon(unsigned int xid, struct cifsSe
 #endif /* CIFS_WEAK_PW_HASH */
 		SMBNTencrypt(tcon->password, ses->server->cryptkey, bcc_ptr);
 
-		bcc_ptr += CIFS_SESS_KEY_SIZE;
+		bcc_ptr += CIFS_AUTH_RESP_SIZE;
 		if (ses->capabilities & CAP_UNICODE) {
 			/* must align unicode strings */
 			*bcc_ptr = 0; /* null byte password */

@@ -1126,15 +1126,13 @@ int pdc_iodc_print(const unsigned char *
 	unsigned int i;
 	unsigned long flags;
 
-	for (i = 0; i < count && i < 79;) {
+	for (i = 0; i < count;) {
 		switch(str[i]) {
 		case '\n':
 			iodc_dbuf[i+0] = '\r';
 			iodc_dbuf[i+1] = '\n';
 			i += 2;
 			goto print;
-		case '\b':	/* BS */
-			i--; /* overwrite last */
 		default:
 			iodc_dbuf[i] = str[i];
 			i++;

@@ -1142,15 +1140,6 @@ int pdc_iodc_print(const unsigned char *
 		}
 	}
 
-	/* if we're at the end of line, and not already inserting a newline,
-	 * insert one anyway. iodc console doesn't claim to support >79 char
-	 * lines. don't account for this in the return value.
-	 */
-	if (i == 79 && iodc_dbuf[i-1] != '\n') {
-		iodc_dbuf[i+0] = '\r';
-		iodc_dbuf[i+1] = '\n';
-	}
-
 print:
         spin_lock_irqsave(&pdc_lock, flags);
         real32_call(PAGE0->mem_cons.iodc_io,

@@ -430,9 +430,6 @@ static int watchdog_enable(int cpu)
 		wake_up_process(p);
 	}
 
-	/* if any cpu succeeds, watchdog is considered enabled for the system */
-	watchdog_enabled = 1;
-
 	return 0;
 }
 

@@ -460,12 +457,16 @@ static void watchdog_disable(int cpu)
 static void watchdog_enable_all_cpus(void)
 {
 	int cpu;
-	int result = 0;
+
+	watchdog_enabled = 0;
 
 	for_each_online_cpu(cpu)
-		result += watchdog_enable(cpu);
+		if (!watchdog_enable(cpu))
+			/* if any cpu succeeds, watchdog is considered
+			   enabled for the system */
+			watchdog_enabled = 1;
 
-	if (result)
+	if (!watchdog_enabled)
 		printk(KERN_ERR "watchdog: failed to be enabled on some cpus\n");
 
 }

@@ -497,10 +497,12 @@ int proc_dowatchdog_enabled(struct ctl_t
 {
 	proc_dointvec(table, write, buffer, length, ppos);
 
-	if (watchdog_enabled)
-		watchdog_enable_all_cpus();
-	else
-		watchdog_disable_all_cpus();
+	if (write) {
+		if (watchdog_enabled)
+			watchdog_enable_all_cpus();
+		else
+			watchdog_disable_all_cpus();
+	}
 	return 0;
 }
 

@@ -4930,9 +4930,9 @@ struct cgroup_subsys mem_cgroup_subsys =
 static int __init enable_swap_account(char *s)
 {
 	/* consider enabled if no parameter or 1 is given */
-	if (!s || !strcmp(s, "1"))
+	if (!(*s) || !strcmp(s, "=1"))
 		really_do_swap_account = 1;
-	else if (!strcmp(s, "0"))
+	else if (!strcmp(s, "=0"))
 		really_do_swap_account = 0;
 	return 1;
 }

@@ -4940,7 +4940,7 @@ __setup("swapaccount", enable_swap_accou
 
 static int __init disable_swap_account(char *s)
 {
-	enable_swap_account("0");
+	enable_swap_account("=0");
 	return 1;
 }
 __setup("noswapaccount", disable_swap_account);

@@ -1872,8 +1872,7 @@ static int alloc_callchain_buffers(void)
 	 * accessed from NMI. Use a temporary manual per cpu allocation
 	 * until that gets sorted out.
 	 */
-	size = sizeof(*entries) + sizeof(struct perf_callchain_entry *) *
-		num_possible_cpus();
+	size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]);
 
 	entries = kzalloc(size, GFP_KERNEL);
 	if (!entries)

@@ -2100,7 +2100,7 @@ find_get_context(struct pmu *pmu, struct
 	unsigned long flags;
 	int ctxn, err;
 
-	if (!task && cpu != -1) {
+	if (!task) {
 		/* Must be root to operate on a CPU event: */
 		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
 			return ERR_PTR(-EACCES);

@@ -2105,9 +2105,6 @@ find_get_context(struct pmu *pmu, struct
 		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
 			return ERR_PTR(-EACCES);
 
-		if (cpu < 0 || cpu >= nr_cpumask_bits)
-			return ERR_PTR(-EINVAL);
-
 		/*
 		 * We could be clever and allow to attach a event to an
 		 * offline CPU and activate it when the CPU comes up, but

@@ -5304,6 +5301,11 @@ perf_event_alloc(struct perf_event_attr
 	struct hw_perf_event *hwc;
 	long err;
 
+	if ((unsigned)cpu >= nr_cpu_ids) {
+		if (!task || cpu != -1)
+			return ERR_PTR(-EINVAL);
+	}
+
 	event = kzalloc(sizeof(*event), GFP_KERNEL);
 	if (!event)
 		return ERR_PTR(-ENOMEM);

@@ -5352,7 +5354,7 @@ perf_event_alloc(struct perf_event_attr
 
 	if (!overflow_handler && parent_event)
 		overflow_handler = parent_event->overflow_handler;
-	
+
 	event->overflow_handler	= overflow_handler;
 
 	if (attr->disabled)

@@ -320,6 +320,7 @@ static int unload_when_empty = 1;
 static int add_smi(struct smi_info *smi);
 static int try_smi_init(struct smi_info *smi);
 static void cleanup_one_si(struct smi_info *to_clean);
+static void cleanup_ipmi_si(void);
 
 static ATOMIC_NOTIFIER_HEAD(xaction_notifier_list);
 static int register_xaction_notifier(struct notifier_block *nb)

@@ -3435,16 +3436,7 @@ static int __devinit init_ipmi_si(void)
 	mutex_lock(&smi_infos_lock);
 	if (unload_when_empty && list_empty(&smi_infos)) {
 		mutex_unlock(&smi_infos_lock);
-#ifdef CONFIG_PCI
-		if (pci_registered)
-			pci_unregister_driver(&ipmi_pci_driver);
-#endif
-
-#ifdef CONFIG_PPC_OF
-		if (of_registered)
-			of_unregister_platform_driver(&ipmi_of_platform_driver);
-#endif
-		driver_unregister(&ipmi_driver.driver);
+		cleanup_ipmi_si();
 		printk(KERN_WARNING PFX
 		       "Unable to find any System Interface(s)\n");
 		return -ENODEV;

@@ -733,7 +733,7 @@ int ssb_pcmcia_get_invariants(struct ssb
 
 	/* Fetch the vendor specific tuples. */
 	res = pcmcia_loop_tuple(bus->host_pcmcia, SSB_PCMCIA_CIS,
-				ssb_pcmcia_do_get_invariants, sprom);
+				ssb_pcmcia_do_get_invariants, iv);
 	if ((res == 0) || (res == -ENOSPC))
 		return 0;
 

@@ -53,7 +53,6 @@
 #define DBG_BLKDEV      0x0100
 #define DBG_RX          0x0200
 #define DBG_TX          0x0400
-static DEFINE_MUTEX(nbd_mutex);
 static unsigned int debugflags;
 #endif /* NDEBUG */
 

@@ -718,11 +717,9 @@ static int nbd_ioctl(struct block_device
 	dprintk(DBG_IOCTL, "%s: nbd_ioctl cmd=%s(0x%x) arg=%lu\n",
 			lo->disk->disk_name, ioctl_cmd_to_ascii(cmd), cmd, arg);
 
-	mutex_lock(&nbd_mutex);
 	mutex_lock(&lo->tx_lock);
 	error = __nbd_ioctl(bdev, lo, cmd, arg);
 	mutex_unlock(&lo->tx_lock);
-	mutex_unlock(&nbd_mutex);
 
 	return error;
 }

@@ -161,6 +161,12 @@ extern void register_page_bootmem_info_n
 extern void put_page_bootmem(struct page *page);
 #endif
 
+/*
+ * Lock for memory hotplug guarantees 1) all callbacks for memory hotplug
+ * notifier will be called under this. 2) offline/online/add/remove memory
+ * will not run simultaneously.
+ */
+
 void lock_memory_hotplug(void);
 void unlock_memory_hotplug(void);
 

@@ -407,6 +407,7 @@ int online_pages(unsigned long pfn, unsi
 	int ret;
 	struct memory_notify arg;
 
+	lock_memory_hotplug();
 	arg.start_pfn = pfn;
 	arg.nr_pages = nr_pages;
 	arg.status_change_nid = -1;

@@ -419,6 +420,7 @@ int online_pages(unsigned long pfn, unsi
 	ret = notifier_to_errno(ret);
 	if (ret) {
 		memory_notify(MEM_CANCEL_ONLINE, &arg);
+		unlock_memory_hotplug();
 		return ret;
 	}
 	/*

@@ -443,6 +445,7 @@ int online_pages(unsigned long pfn, unsi
 		printk(KERN_DEBUG "online_pages %lx at %lx failed\n",
 			nr_pages, pfn);
 		memory_notify(MEM_CANCEL_ONLINE, &arg);
+		unlock_memory_hotplug();
 		return ret;
 	}
 

@@ -467,6 +470,7 @@ int online_pages(unsigned long pfn, unsi
 
 	if (onlined_pages)
 		memory_notify(MEM_ONLINE, &arg);
+	unlock_memory_hotplug();
 
 	return 0;
 }

@@ -21,7 +21,7 @@
 #define MAX_BRIGHTNESS		(0xFF)
 #define MIN_BRIGHTNESS		(0)
 
-#define CURRENT_MASK		(0x1F << 1)
+#define CURRENT_BITMASK		(0x1F << 1)
 
 struct pm860x_backlight_data {
 	struct pm860x_chip *chip;

@@ -85,7 +85,7 @@ static int pm860x_backlight_set(struct b
 	if ((data->current_brightness == 0) && brightness) {
 		if (data->iset) {
 			ret = pm860x_set_bits(data->i2c, wled_idc(data->port),
-					      CURRENT_MASK, data->iset);
+					      CURRENT_BITMASK, data->iset);
 			if (ret < 0)
 				goto out;
 		}

@@ -325,12 +325,16 @@ void dio_end_io(struct bio *bio, int err
 }
 EXPORT_SYMBOL_GPL(dio_end_io);
 
-static int
+static void
 dio_bio_alloc(struct dio *dio, struct block_device *bdev,
 		sector_t first_sector, int nr_vecs)
 {
 	struct bio *bio;
 
+	/*
+	 * bio_alloc() is guaranteed to return a bio when called with
+	 * __GFP_WAIT and we request a valid number of vectors.
+	 */
 	bio = bio_alloc(GFP_KERNEL, nr_vecs);
 
 	bio->bi_bdev = bdev;

@@ -342,7 +346,6 @@ dio_bio_alloc(struct dio *dio, struct bl
 
 	dio->bio = bio;
 	dio->logical_offset_in_bio = dio->cur_page_fs_offset;
-	return 0;
 }
 
 /*

@@ -583,8 +586,9 @@ static int dio_new_bio(struct dio *dio,
 		goto out;
 	sector = start_sector << (dio->blkbits - 9);
 	nr_pages = min(dio->pages_in_io, bio_get_nr_vecs(dio->map_bh.b_bdev));
+	nr_pages = min(nr_pages, BIO_MAX_PAGES);
 	BUG_ON(nr_pages <= 0);
-	ret = dio_bio_alloc(dio, dio->map_bh.b_bdev, sector, nr_pages);
+	dio_bio_alloc(dio, dio->map_bh.b_bdev, sector, nr_pages);
 	dio->boundary = 0;
 out:
 	return ret;

@@ -194,6 +194,24 @@ void generic_smp_call_function_interrupt
 	list_for_each_entry_rcu(data, &call_function.queue, csd.list) {
 		int refs;
 
+		/*
+		 * Since we walk the list without any locks, we might
+		 * see an entry that was completed, removed from the
+		 * list and is in the process of being reused.
+		 *
+		 * We must check that the cpu is in the cpumask before
+		 * checking the refs, and both must be set before
+		 * executing the callback on this cpu.
+		 */
+
+		if (!cpumask_test_cpu(cpu, data->cpumask))
+			continue;
+
+		smp_rmb();
+
+		if (atomic_read(&data->refs) == 0)
+			continue;
+
 		if (!cpumask_test_and_clear_cpu(cpu, data->cpumask))
 			continue;
 

@@ -202,6 +220,8 @@ void generic_smp_call_function_interrupt
 		refs = atomic_dec_return(&data->refs);
 		WARN_ON(refs < 0);
 		if (!refs) {
+			WARN_ON(!cpumask_empty(data->cpumask));
+
 			raw_spin_lock(&call_function.lock);
 			list_del_rcu(&data->csd.list);
 			raw_spin_unlock(&call_function.lock);

@@ -453,11 +473,21 @@ void smp_call_function_many(const struct
 
 	data = &__get_cpu_var(cfd_data);
 	csd_lock(&data->csd);
+	BUG_ON(atomic_read(&data->refs) || !cpumask_empty(data->cpumask));
 
 	data->csd.func = func;
 	data->csd.info = info;
 	cpumask_and(data->cpumask, mask, cpu_online_mask);
 	cpumask_clear_cpu(this_cpu, data->cpumask);
+
+	/*
+	 * To ensure the interrupt handler gets an complete view
+	 * we order the cpumask and refs writes and order the read
+	 * of them in the interrupt handler.  In addition we may
+	 * only clear our own cpu bit from the mask.
+	 */
+	smp_wmb();
+
 	atomic_set(&data->refs, cpumask_weight(data->cpumask));
 
 	raw_spin_lock_irqsave(&call_function.lock, flags);

@@ -518,22 +518,21 @@ static int prism2_config(struct pcmcia_d
 	hw_priv->link = link;
 
 	/*
-	 * Make sure the IRQ handler cannot proceed until at least
-	 * dev->base_addr is initialized.
+	 * We enable IRQ here, but IRQ handler will not proceed
+	 * until dev->base_addr is set below. This protect us from
+	 * receive interrupts when driver is not initialized.
 	 */
-	spin_lock_irqsave(&local->irq_init_lock, flags);
-
 	ret = pcmcia_request_irq(link, prism2_interrupt);
 	if (ret)
-		goto failed_unlock;
+		goto failed;
 
 	ret = pcmcia_enable_device(link);
 	if (ret)
-		goto failed_unlock;
+		goto failed;
 
+	spin_lock_irqsave(&local->irq_init_lock, flags);
 	dev->irq = link->irq;
 	dev->base_addr = link->resource[0]->start;
-
 	spin_unlock_irqrestore(&local->irq_init_lock, flags);
 
 	local->shutdown = 0;

@@ -546,8 +545,6 @@ static int prism2_config(struct pcmcia_d
 
 	return ret;
 
- failed_unlock:
-	spin_unlock_irqrestore(&local->irq_init_lock, flags);
  failed:
 	kfree(hw_priv);
 	prism2_release((u_long)link);

@@ -5159,9 +5159,10 @@ static int add_new_disk(mddev_t * mddev,
 		/* set saved_raid_disk if appropriate */
 		if (!mddev->persistent) {
 			if (info->state & (1<<MD_DISK_SYNC)  &&
-			    info->raid_disk < mddev->raid_disks)
+			    info->raid_disk < mddev->raid_disks) {
 				rdev->raid_disk = info->raid_disk;
-			else
+				set_bit(In_sync, &rdev->flags);
+			} else
 				rdev->raid_disk = -1;
 		} else
 			super_types[mddev->major_version].

@@ -6042,7 +6042,8 @@ static int md_thread(void * arg)
 			 || kthread_should_stop(),
 			 thread->timeout);
 
-		if (test_and_clear_bit(THREAD_WAKEUP, &thread->flags))
+		clear_bit(THREAD_WAKEUP, &thread->flags);
+		if (!kthread_should_stop())
 			thread->run(thread->mddev);
 	}
 

@@ -288,10 +288,12 @@ static int md_make_request(struct reques
 	int rv;
 	int cpu;
 
-	if (mddev == NULL || mddev->pers == NULL) {
+	if (mddev == NULL || mddev->pers == NULL
+	    || !mddev->ready) {
 		bio_io_error(bio);
 		return 0;
 	}
+	smp_rmb(); /* Ensure implications of  'active' are visible */
 	rcu_read_lock();
 	if (mddev->suspended) {
 		DEFINE_WAIT(__wait);

@@ -4564,7 +4566,8 @@ int md_run(mddev_t *mddev)
 	mddev->safemode_timer.data = (unsigned long) mddev;
 	mddev->safemode_delay = (200 * HZ)/1000 +1; /* 200 msec delay */
 	mddev->in_sync = 1;
-
+	smp_wmb();
+	mddev->ready = 1;
 	list_for_each_entry(rdev, &mddev->disks, same_set)
 		if (rdev->raid_disk >= 0) {
 			char nm[20];

@@ -4725,6 +4728,7 @@ EXPORT_SYMBOL_GPL(md_stop_writes);
 
 void md_stop(mddev_t *mddev)
 {
+	mddev->ready = 0;
 	mddev->pers->stop(mddev);
 	if (mddev->pers->sync_request && mddev->to_remove == NULL)
 		mddev->to_remove = &md_redundancy_group;

@@ -148,7 +148,8 @@ struct mddev_s
 						       * are happening, so run/
 						       * takeover/stop are not safe
 						       */
-
+	int				ready; /* See when safe to pass
+						* IO requests down */
 	struct gendisk			*gendisk;
 
 	struct kobject			kobj;

@@ -3117,7 +3117,7 @@ level_store(mddev_t *mddev, const char *
 		char nm[20];
 		if (rdev->raid_disk < 0)
 			continue;
-		if (rdev->new_raid_disk > mddev->raid_disks)
+		if (rdev->new_raid_disk >= mddev->raid_disks)
 			rdev->new_raid_disk = -1;
 		if (rdev->new_raid_disk == rdev->raid_disk)
 			continue;

@@ -610,7 +610,7 @@ static struct scsi_host_template mpc52xx
 };
 
 static struct ata_port_operations mpc52xx_ata_port_ops = {
-	.inherits		= &ata_sff_port_ops,
+	.inherits		= &ata_bmdma_port_ops,
 	.sff_dev_select		= mpc52xx_ata_dev_select,
 	.set_piomode		= mpc52xx_ata_set_piomode,
 	.set_dmamode		= mpc52xx_ata_set_dmamode,

@@ -287,6 +287,7 @@ static int md_make_request(struct reques
 	mddev_t *mddev = q->queuedata;
 	int rv;
 	int cpu;
+	unsigned int sectors;
 
 	if (mddev == NULL || mddev->pers == NULL
 	    || !mddev->ready) {

@@ -311,12 +312,16 @@ static int md_make_request(struct reques
 	atomic_inc(&mddev->active_io);
 	rcu_read_unlock();
 
+	/*
+	 * save the sectors now since our bio can
+	 * go away inside make_request
+	 */
+	sectors = bio_sectors(bio);
 	rv = mddev->pers->make_request(mddev, bio);
 
 	cpu = part_stat_lock();
 	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
-		      bio_sectors(bio));
+	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors);
 	part_stat_unlock();
 
 	if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)

@@ -404,12 +404,15 @@ static int rpm_suspend(struct device *de
 		goto out;
 	}
 
+	/* Maybe the parent is now able to suspend. */
 	if (parent && !parent->power.ignore_children) {
-		spin_unlock_irq(&dev->power.lock);
+		spin_unlock(&dev->power.lock);
 
-		pm_request_idle(parent);
+		spin_lock(&parent->power.lock);
+		rpm_idle(parent, RPM_ASYNC);
+		spin_unlock(&parent->power.lock);
 
-		spin_lock_irq(&dev->power.lock);
+		spin_lock(&dev->power.lock);
 	}
 
  out:

@@ -817,7 +817,7 @@ static int ethtool_get_regs(struct net_d
 	if (regs.len > reglen)
 		regs.len = reglen;
 
-	regbuf = vmalloc(reglen);
+	regbuf = vzalloc(reglen);
 	if (!regbuf)
 		return -ENOMEM;
 

@@ -688,7 +688,8 @@ skip_mount_setup:
 	sbp[0]->s_state =
 		cpu_to_le16(le16_to_cpu(sbp[0]->s_state) & ~NILFS_VALID_FS);
 	/* synchronize sbp[1] with sbp[0] */
-	memcpy(sbp[1], sbp[0], nilfs->ns_sbsize);
+	if (sbp[1])
+		memcpy(sbp[1], sbp[0], nilfs->ns_sbsize);
 	return nilfs_commit_super(sbi, NILFS_SB_COMMIT_ALL);
 }
 

@@ -493,9 +493,6 @@ static int tpm_tis_init(struct device *d
 		 "1.2 TPM (device-id 0x%X, rev-id %d)\n",
 		 vendor >> 16, ioread8(chip->vendor.iobase + TPM_RID(0)));
 
-	if (is_itpm(to_pnp_dev(dev)))
-		itpm = 1;
-
 	if (itpm)
 		dev_info(dev, "Intel iTPM workaround enabled\n");
 

@@ -637,6 +634,9 @@ static int __devinit tpm_tis_pnp_init(st
 	else
 		interrupts = 0;
 
+	if (is_itpm(pnp_dev))
+		itpm = 1;
+
 	return tpm_tis_init(&pnp_dev->dev, start, len, irq);
 }
 

@@ -364,12 +364,14 @@ unsigned long tpm_calc_ordinal_duration(
 		    tpm_protected_ordinal_duration[ordinal &
 						   TPM_PROTECTED_ORDINAL_MASK];
 
-	if (duration_idx != TPM_UNDEFINED)
+	if (duration_idx != TPM_UNDEFINED) {
 		duration = chip->vendor.duration[duration_idx];
-	if (duration <= 0)
+		/* if duration is 0, it's because chip->vendor.duration wasn't */
+		/* filled yet, so we set the lowest timeout just to give enough */
+		/* time for tpm_get_timeouts() to succeed */
+		return (duration <= 0 ? HZ : duration);
+	} else
 		return 2 * 60 * HZ;
-	else
-		return duration;
 }
 EXPORT_SYMBOL_GPL(tpm_calc_ordinal_duration);
 

@@ -577,9 +577,11 @@ duration:
 	if (rc)
 		return;
 
-	if (be32_to_cpu(tpm_cmd.header.out.return_code)
-	    != 3 * sizeof(u32))
+	if (be32_to_cpu(tpm_cmd.header.out.return_code) != 0 ||
+	    be32_to_cpu(tpm_cmd.header.out.length)
+	    != sizeof(tpm_cmd.header.out) + sizeof(u32) + 3 * sizeof(u32))
 		return;
+
 	duration_cap = &tpm_cmd.params.getcap_out.cap.duration;
 	chip->vendor.duration[TPM_SHORT] =
 	    usecs_to_jiffies(be32_to_cpu(duration_cap->tpm_short));

@@ -923,6 +925,18 @@ ssize_t tpm_show_caps_1_2(struct device
 }
 EXPORT_SYMBOL_GPL(tpm_show_caps_1_2);
 
+ssize_t tpm_show_timeouts(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	struct tpm_chip *chip = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%d %d %d\n",
+	               jiffies_to_usecs(chip->vendor.duration[TPM_SHORT]),
+	               jiffies_to_usecs(chip->vendor.duration[TPM_MEDIUM]),
+	               jiffies_to_usecs(chip->vendor.duration[TPM_LONG]));
+}
+EXPORT_SYMBOL_GPL(tpm_show_timeouts);
+
 ssize_t tpm_store_cancel(struct device *dev, struct device_attribute *attr,
 			const char *buf, size_t count)
 {

@@ -56,6 +56,8 @@ extern ssize_t tpm_show_owned(struct dev
 				char *);
 extern ssize_t tpm_show_temp_deactivated(struct device *,
 					 struct device_attribute *attr, char *);
+extern ssize_t tpm_show_timeouts(struct device *,
+				 struct device_attribute *attr, char *);
 
 struct tpm_chip;
 

@@ -376,6 +376,7 @@ static DEVICE_ATTR(temp_deactivated, S_I
 		   NULL);
 static DEVICE_ATTR(caps, S_IRUGO, tpm_show_caps_1_2, NULL);
 static DEVICE_ATTR(cancel, S_IWUSR | S_IWGRP, NULL, tpm_store_cancel);
+static DEVICE_ATTR(timeouts, S_IRUGO, tpm_show_timeouts, NULL);
 
 static struct attribute *tis_attrs[] = {
 	&dev_attr_pubek.attr,

@@ -385,7 +386,8 @@ static struct attribute *tis_attrs[] = {
 	&dev_attr_owned.attr,
 	&dev_attr_temp_deactivated.attr,
 	&dev_attr_caps.attr,
-	&dev_attr_cancel.attr, NULL,
+	&dev_attr_cancel.attr,
+	&dev_attr_timeouts.attr, NULL,
 };
 
 static struct attribute_group tis_attr_grp = {

@@ -65,6 +65,8 @@ static struct nlmsg_perm nlmsg_route_per
 	{ RTM_NEWADDRLABEL,	NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
 	{ RTM_DELADDRLABEL,	NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
 	{ RTM_GETADDRLABEL,	NETLINK_ROUTE_SOCKET__NLMSG_READ  },
+	{ RTM_GETDCB,		NETLINK_ROUTE_SOCKET__NLMSG_READ  },
+	{ RTM_SETDCB,		NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
 };
 
 static struct nlmsg_perm nlmsg_firewall_perms[] =

@@ -2525,7 +2525,10 @@ static int selinux_inode_init_security(s
 	sid = tsec->sid;
 	newsid = tsec->create_sid;
 
-	if (!newsid || !(sbsec->flags & SE_SBLABELSUPP)) {
+	if ((sbsec->flags & SE_SBINITIALIZED) &&
+	    (sbsec->behavior == SECURITY_FS_USE_MNTPOINT))
+		newsid = sbsec->mntpoint_sid;
+	else if (!newsid || !(sbsec->flags & SE_SBLABELSUPP)) {
 		rc = security_transition_sid(sid, dsec->sid,
 					     inode_mode_to_security_class(inode->i_mode),
 					     &newsid);

@@ -27,7 +27,7 @@
 #include <asm/irq_regs.h>
 #include <linux/perf_event.h>
 
-int watchdog_enabled;
+int watchdog_enabled = 1;
 int __read_mostly softlockup_thresh = 60;
 
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);

@@ -43,9 +43,6 @@ static DEFINE_PER_CPU(unsigned long, hrt
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
 #endif
 
-static int no_watchdog;
-
-
 /* boot commands */
 /*
  * Should we panic when a soft-lockup or hard-lockup occurs:

@@ -75,7 +72,7 @@ __setup("softlockup_panic=", softlockup_
 
 static int __init nowatchdog_setup(char *str)
 {
-	no_watchdog = 1;
+	watchdog_enabled = 0;
 	return 1;
 }
 __setup("nowatchdog", nowatchdog_setup);

@@ -83,7 +80,7 @@ __setup("nowatchdog", nowatchdog_setup);
 /* deprecated */
 static int __init nosoftlockup_setup(char *str)
 {
-	no_watchdog = 1;
+	watchdog_enabled = 0;
 	return 1;
 }
 __setup("nosoftlockup", nosoftlockup_setup);

@@ -475,9 +472,6 @@ static void watchdog_disable_all_cpus(vo
 {
 	int cpu;
 
-	if (no_watchdog)
-		return;
-
 	for_each_online_cpu(cpu)
 		watchdog_disable(cpu);
 

@@ -531,7 +525,8 @@ cpu_callback(struct notifier_block *nfb,
 		break;
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		err = watchdog_enable(hotcpu);
+		if (watchdog_enabled)
+			err = watchdog_enable(hotcpu);
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_UP_CANCELED:

@@ -556,9 +551,6 @@ static int __init spawn_watchdog_task(vo
 	void *cpu = (void *)(long)smp_processor_id();
 	int err;
 
-	if (no_watchdog)
-		return 0;
-
 	err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
 	WARN_ON(notifier_to_errno(err));
 

@@ -571,6 +571,7 @@ struct sysrq_state {
 	unsigned int alt_use;
 	bool active;
 	bool need_reinject;
+	bool reinjecting;
 };
 
 static void sysrq_reinject_alt_sysrq(struct work_struct *work)

@@ -581,6 +582,10 @@ static void sysrq_reinject_alt_sysrq(str
 	unsigned int alt_code = sysrq->alt_use;
 
 	if (sysrq->need_reinject) {
+		/* we do not want the assignment to be reordered */
+		sysrq->reinjecting = true;
+		mb();
+
 		/* Simulate press and release of Alt + SysRq */
 		input_inject_event(handle, EV_KEY, alt_code, 1);
 		input_inject_event(handle, EV_KEY, KEY_SYSRQ, 1);

@@ -589,6 +594,9 @@ static void sysrq_reinject_alt_sysrq(str
 		input_inject_event(handle, EV_KEY, KEY_SYSRQ, 0);
 		input_inject_event(handle, EV_KEY, alt_code, 0);
 		input_inject_event(handle, EV_SYN, SYN_REPORT, 1);
+
+		mb();
+		sysrq->reinjecting = false;
 	}
 }
 

@@ -599,6 +607,13 @@ static bool sysrq_filter(struct input_ha
 	bool was_active = sysrq->active;
 	bool suppress;
 
+	/*
+	 * Do not filter anything if we are in the process of re-injecting
+	 * Alt+SysRq combination.
+	 */
+	if (sysrq->reinjecting)
+		return false;
+
 	switch (type) {
 
 	case EV_SYN:

@@ -629,7 +644,7 @@ static bool sysrq_filter(struct input_ha
 				sysrq->alt_use = sysrq->alt;
 				/*
 				 * If nothing else will be pressed we'll need
-				 * to * re-inject Alt-SysRq keysroke.
+				 * to re-inject Alt-SysRq keysroke.
 				 */
 				sysrq->need_reinject = true;
 			}

@@ -73,7 +73,6 @@ static int input_defuzz_abs_event(int va
  * dev->event_lock held and interrupts disabled.
  */
 static void input_pass_event(struct input_dev *dev,
-			     struct input_handler *src_handler,
 			     unsigned int type, unsigned int code, int value)
 {
 	struct input_handler *handler;

@@ -92,15 +91,6 @@ static void input_pass_event(struct inpu
 				continue;
 
 			handler = handle->handler;
-
-			/*
-			 * If this is the handler that injected this
-			 * particular event we want to skip it to avoid
-			 * filters firing again and again.
-			 */
-			if (handler == src_handler)
-				continue;
-
 			if (!handler->filter) {
 				if (filtered)
 					break;

@@ -130,7 +120,7 @@ static void input_repeat_key(unsigned lo
 	if (test_bit(dev->repeat_key, dev->key) &&
 	    is_event_supported(dev->repeat_key, dev->keybit, KEY_MAX)) {
 
-		input_pass_event(dev, NULL, EV_KEY, dev->repeat_key, 2);
+		input_pass_event(dev, EV_KEY, dev->repeat_key, 2);
 
 		if (dev->sync) {
 			/*

@@ -139,7 +129,7 @@ static void input_repeat_key(unsigned lo
 			 * Otherwise assume that the driver will send
 			 * SYN_REPORT once it's done.
 			 */
-			input_pass_event(dev, NULL, EV_SYN, SYN_REPORT, 1);
+			input_pass_event(dev, EV_SYN, SYN_REPORT, 1);
 		}
 
 		if (dev->rep[REP_PERIOD])

@@ -172,7 +162,6 @@ static void input_stop_autorepeat(struct
 #define INPUT_PASS_TO_ALL	(INPUT_PASS_TO_HANDLERS | INPUT_PASS_TO_DEVICE)
 
 static int input_handle_abs_event(struct input_dev *dev,
-				  struct input_handler *src_handler,
 				  unsigned int code, int *pval)
 {
 	bool is_mt_event;

@@ -216,15 +205,13 @@ static int input_handle_abs_event(struct
 	/* Flush pending "slot" event */
 	if (is_mt_event && dev->slot != input_abs_get_val(dev, ABS_MT_SLOT)) {
 		input_abs_set_val(dev, ABS_MT_SLOT, dev->slot);
-		input_pass_event(dev, src_handler,
-				 EV_ABS, ABS_MT_SLOT, dev->slot);
+		input_pass_event(dev, EV_ABS, ABS_MT_SLOT, dev->slot);
 	}
 
 	return INPUT_PASS_TO_HANDLERS;
 }
 
 static void input_handle_event(struct input_dev *dev,
-			       struct input_handler *src_handler,
 			       unsigned int type, unsigned int code, int value)
 {
 	int disposition = INPUT_IGNORE_EVENT;

@@ -277,8 +264,7 @@ static void input_handle_event(struct in
 
 	case EV_ABS:
 		if (is_event_supported(code, dev->absbit, ABS_MAX))
-			disposition = input_handle_abs_event(dev, src_handler,
-							     code, &value);
+			disposition = input_handle_abs_event(dev, code, &value);
 
 		break;
 

@@ -336,7 +322,7 @@ static void input_handle_event(struct in
 		dev->event(dev, type, code, value);
 
 	if (disposition & INPUT_PASS_TO_HANDLERS)
-		input_pass_event(dev, src_handler, type, code, value);
+		input_pass_event(dev, type, code, value);
 }
 
 /**

@@ -365,7 +351,7 @@ void input_event(struct input_dev *dev,
 
 		spin_lock_irqsave(&dev->event_lock, flags);
 		add_input_randomness(type, code, value);
-		input_handle_event(dev, NULL, type, code, value);
+		input_handle_event(dev, type, code, value);
 		spin_unlock_irqrestore(&dev->event_lock, flags);
 	}
 }

@@ -395,8 +381,7 @@ void input_inject_event(struct input_han
 		rcu_read_lock();
 		grab = rcu_dereference(dev->grab);
 		if (!grab || grab == handle)
-			input_handle_event(dev, handle->handler,
-					   type, code, value);
+			input_handle_event(dev, type, code, value);
 		rcu_read_unlock();
 
 		spin_unlock_irqrestore(&dev->event_lock, flags);

@@ -609,10 +594,10 @@ static void input_dev_release_keys(struc
 		for (code = 0; code <= KEY_MAX; code++) {
 			if (is_event_supported(code, dev->keybit, KEY_MAX) &&
 			    __test_and_clear_bit(code, dev->key)) {
-				input_pass_event(dev, NULL, EV_KEY, code, 0);
+				input_pass_event(dev, EV_KEY, code, 0);
 			}
 		}
-		input_pass_event(dev, NULL, EV_SYN, SYN_REPORT, 1);
+		input_pass_event(dev, EV_SYN, SYN_REPORT, 1);
 	}
 }
 

@@ -887,9 +872,9 @@ int input_set_keycode(struct input_dev *
 	    !is_event_supported(old_keycode, dev->keybit, KEY_MAX) &&
 	    __test_and_clear_bit(old_keycode, dev->key)) {
 
-		input_pass_event(dev, NULL, EV_KEY, old_keycode, 0);
+		input_pass_event(dev, EV_KEY, old_keycode, 0);
 		if (dev->sync)
-			input_pass_event(dev, NULL, EV_SYN, SYN_REPORT, 1);
+			input_pass_event(dev, EV_SYN, SYN_REPORT, 1);
 	}
 
  out:

@@ -46,7 +46,7 @@
 #include <asm/irq_regs.h>
 
 /* Whether we react on sysrq keys or just ignore them */
-static int __read_mostly sysrq_enabled = 1;
+static int __read_mostly sysrq_enabled = SYSRQ_DEFAULT_ENABLE;
 static bool __read_mostly sysrq_always_enabled;
 
 static bool sysrq_on(void)

@@ -17,6 +17,9 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 
+/* Enable/disable SYSRQ support by default (0==no, 1==yes). */
+#define SYSRQ_DEFAULT_ENABLE	1
+
 /* Possible values of bitmask for enabling sysrq functions */
 /* 0x0001 is reserved for enable everything */
 #define SYSRQ_ENABLE_LOG	0x0002

@@ -169,7 +169,8 @@ static int proc_taint(struct ctl_table *
 #endif
 
 #ifdef CONFIG_MAGIC_SYSRQ
-static int __sysrq_enabled; /* Note: sysrq code ises it's own private copy */
+/* Note: sysrq code uses it's own private copy */
+static int __sysrq_enabled = SYSRQ_DEFAULT_ENABLE;
 
 static int sysrq_sysctl_handler(ctl_table *table, int write,
 				void __user *buffer, size_t *lenp,

@@ -186,10 +186,10 @@ int oprofile_add_data(struct op_entry *e
 int oprofile_add_data64(struct op_entry *entry, u64 val);
 int oprofile_write_commit(struct op_entry *entry);
 
-#ifdef CONFIG_PERF_EVENTS
+#ifdef CONFIG_HW_PERF_EVENTS
 int __init oprofile_perf_init(struct oprofile_operations *ops);
 void oprofile_perf_exit(void);
 char *op_name_from_perf_id(void);
-#endif /* CONFIG_PERF_EVENTS */
+#endif /* CONFIG_HW_PERF_EVENTS */
 
 #endif /* OPROFILE_H */

@@ -97,21 +97,31 @@ void show_regs(struct pt_regs *regs)
 
 void show_regs_common(void)
 {
-	const char *board, *product;
+	const char *vendor, *product, *board;
 
-	board = dmi_get_system_info(DMI_BOARD_NAME);
-	if (!board)
-		board = "";
+	vendor = dmi_get_system_info(DMI_SYS_VENDOR);
+	if (!vendor)
+		vendor = "";
 	product = dmi_get_system_info(DMI_PRODUCT_NAME);
 	if (!product)
 		product = "";
 
+	/* Board Name is optional */
+	board = dmi_get_system_info(DMI_BOARD_NAME);
+
 	printk(KERN_CONT "\n");
-	printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s %s/%s\n",
+	printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s",
 		current->pid, current->comm, print_tainted(),
 		init_utsname()->release,
 		(int)strcspn(init_utsname()->version, " "),
-		init_utsname()->version, board, product);
+		init_utsname()->version);
+	printk(KERN_CONT " ");
+	printk(KERN_CONT "%s %s", vendor, product);
+	if (board) {
+		printk(KERN_CONT "/");
+		printk(KERN_CONT "%s", board);
+	}
+	printk(KERN_CONT "\n");
 }
 
 void flush_thread(void)