Merge branch 'core/percpu' into x86/paravirt

Documentation/block/biodoc.txt

@@ -954,14 +954,14 @@ elevator_allow_merge_fn		called whenever the block layer determines
 				results in some sort of conflict internally,
 				this hook allows it to do that.
 
-elevator_dispatch_fn		fills the dispatch queue with ready requests.
+elevator_dispatch_fn*		fills the dispatch queue with ready requests.
 				I/O schedulers are free to postpone requests by
 				not filling the dispatch queue unless @force
 				is non-zero.  Once dispatched, I/O schedulers
 				are not allowed to manipulate the requests -
 				they belong to generic dispatch queue.
 
-elevator_add_req_fn		called to add a new request into the scheduler
+elevator_add_req_fn*		called to add a new request into the scheduler
 
 elevator_queue_empty_fn		returns true if the merge queue is empty.
 				Drivers shouldn't use this, but rather check
@@ -991,7 +991,7 @@ elevator_activate_req_fn	Called when device driver first sees a request.
 elevator_deactivate_req_fn	Called when device driver decides to delay
 				a request by requeueing it.
 
-elevator_init_fn
+elevator_init_fn*
 elevator_exit_fn		Allocate and free any elevator specific storage
 				for a queue.
 

Documentation/networking/alias.txt

@@ -2,13 +2,13 @@
 IP-Aliasing:
 ============
 
-IP-aliases are additional IP-addresses/masks hooked up to a base 
-interface by adding a colon and a string when running ifconfig. 
-This string is usually numeric, but this is not a must.
-
-IP-Aliases are avail if CONFIG_INET (`standard' IPv4 networking) 
-is configured in the kernel.
+IP-aliases are an obsolete way to manage multiple IP-addresses/masks
+per interface. Newer tools such as iproute2 support multiple
+address/prefixes per interface, but aliases are still supported
+for backwards compatibility.
 
+An alias is formed by adding a colon and a string when running ifconfig.
+This string is usually numeric, but this is not a must.
 
 o Alias creation.
   Alias creation is done by 'magic' interface naming: eg. to create a
@@ -38,16 +38,3 @@ o Relationship with main device
 
   If the base device is shut down the added aliases will be deleted 
   too.
-
-
-Contact
--------
-Please finger or e-mail me:
-   Juan Jose Ciarlante <jjciarla@raiz.uncu.edu.ar>
-
-Updated by Erik Schoenfelder <schoenfr@gaertner.DE>
-
-; local variables:
-; mode: indented-text
-; mode: auto-fill
-; end:

MAINTAINERS

@@ -2836,8 +2836,6 @@ S:	Maintained
 MAC80211
 P:	Johannes Berg
 M:	johannes@sipsolutions.net
-P:	Michael Wu
-M:	flamingice@sourmilk.net
 L:	linux-wireless@vger.kernel.org
 W:	http://linuxwireless.org/
 T:	git kernel.org:/pub/scm/linux/kernel/git/linville/wireless-2.6.git

arch/x86/include/asm/processor.h

@@ -768,7 +768,8 @@ extern int sysenter_setup(void);
 extern struct desc_ptr		early_gdt_descr;
 
 extern void cpu_set_gdt(int);
-extern void switch_to_new_gdt(void);
+extern void switch_to_new_gdt(int);
+extern void load_percpu_segment(int);
 extern void cpu_init(void);
 
 static inline unsigned long get_debugctlmsr(void)

arch/x86/kernel/cpu/common.c

@@ -253,23 +253,28 @@ static char __cpuinit *table_lookup_model(struct cpuinfo_x86 *c)
 
 __u32 cleared_cpu_caps[NCAPINTS] __cpuinitdata;
 
+void load_percpu_segment(int cpu)
+{
+#ifdef CONFIG_X86_32
+	loadsegment(fs, __KERNEL_PERCPU);
+#else
+	loadsegment(gs, 0);
+	wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu));
+#endif
+}
+
 /* Current gdt points %fs at the "master" per-cpu area: after this,
  * it's on the real one. */
-void switch_to_new_gdt(void)
+void switch_to_new_gdt(int cpu)
 {
 	struct desc_ptr gdt_descr;
-	int cpu = smp_processor_id();
 
 	gdt_descr.address = (long)get_cpu_gdt_table(cpu);
 	gdt_descr.size = GDT_SIZE - 1;
 	load_gdt(&gdt_descr);
 	/* Reload the per-cpu base */
-#ifdef CONFIG_X86_32
-	loadsegment(fs, __KERNEL_PERCPU);
-#else
-	loadsegment(gs, 0);
-	wrmsrl(MSR_GS_BASE, (unsigned long)per_cpu(irq_stack_union.gs_base, cpu));
-#endif
+
+	load_percpu_segment(cpu);
 }
 
 static struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {};
@@ -993,7 +998,7 @@ void __cpuinit cpu_init(void)
 	 * and set up the GDT descriptor:
 	 */
 
-	switch_to_new_gdt();
+	switch_to_new_gdt(cpu);
 	loadsegment(fs, 0);
 
 	load_idt((const struct desc_ptr *)&idt_descr);
@@ -1098,7 +1103,7 @@ void __cpuinit cpu_init(void)
 		clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
 
 	load_idt(&idt_descr);
-	switch_to_new_gdt();
+	switch_to_new_gdt(cpu);
 
 	/*
 	 * Set up and load the per-CPU TSS and LDT

arch/x86/kernel/setup_percpu.c

@@ -122,7 +122,7 @@ void __init setup_per_cpu_areas(void)
 		 * area.  Reload any changed state for the boot CPU.
 		 */
 		if (cpu == boot_cpu_id)
-			switch_to_new_gdt();
+			switch_to_new_gdt(cpu);
 
 		DBG("PERCPU: cpu %4d %p\n", cpu, ptr);
 	}

arch/x86/kernel/smpboot.c

@@ -1185,7 +1185,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 void __init native_smp_prepare_boot_cpu(void)
 {
 	int me = smp_processor_id();
-	switch_to_new_gdt();
+	switch_to_new_gdt(me);
 	/* already set me in cpu_online_mask in boot_cpu_init() */
 	cpumask_set_cpu(me, cpu_callout_mask);
 	per_cpu(cpu_state, me) = CPU_ONLINE;

arch/x86/kernel/tlb_uv.c

@@ -259,7 +259,7 @@ const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade,
 		 * the cpu's, all of which are still in the mask.
 		 */
 		__get_cpu_var(ptcstats).ptc_i++;
-		return 0;
+		return flush_mask;
 	}
 
 	/*

arch/x86/kernel/vmlinux_64.lds.S

@@ -22,6 +22,7 @@ PHDRS {
 #ifdef CONFIG_SMP
 	percpu PT_LOAD FLAGS(7);	/* RWE */
 #endif
+	data.init2 PT_LOAD FLAGS(7);	/* RWE */
 	note PT_NOTE FLAGS(0);	/* ___ */
 }
 SECTIONS
@@ -215,7 +216,7 @@ SECTIONS
   /*
    * percpu offsets are zero-based on SMP.  PERCPU_VADDR() changes the
    * output PHDR, so the next output section - __data_nosave - should
-   * switch it back to data.init.  Also, pda should be at the head of
+   * start another section data.init2.  Also, pda should be at the head of
    * percpu area.  Preallocate it and define the percpu offset symbol
    * so that it can be accessed as a percpu variable.
    */
@@ -232,7 +233,7 @@ SECTIONS
   __nosave_begin = .;
   .data_nosave : AT(ADDR(.data_nosave) - LOAD_OFFSET) {
       *(.data.nosave)
-  } :data.init	/* switch back to data.init, see PERCPU_VADDR() above */
+  } :data.init2 /* use another section data.init2, see PERCPU_VADDR() above */
   . = ALIGN(PAGE_SIZE);
   __nosave_end = .;
 

arch/x86/mach-voyager/voyager_smp.c

@@ -1746,12 +1746,13 @@ static void __init voyager_smp_prepare_cpus(unsigned int max_cpus)
 
 static void __cpuinit voyager_smp_prepare_boot_cpu(void)
 {
-	switch_to_new_gdt();
+	int cpu = smp_processor_id();
+	switch_to_new_gdt(cpu);
 
-	cpu_set(smp_processor_id(), cpu_online_map);
-	cpu_set(smp_processor_id(), cpu_callout_map);
-	cpu_set(smp_processor_id(), cpu_possible_map);
-	cpu_set(smp_processor_id(), cpu_present_map);
+	cpu_set(cpu, cpu_online_map);
+	cpu_set(cpu, cpu_callout_map);
+	cpu_set(cpu, cpu_possible_map);
+	cpu_set(cpu, cpu_present_map);
 }
 
 static int __cpuinit voyager_cpu_up(unsigned int cpu)

arch/x86/xen/enlighten.c

@@ -917,6 +917,9 @@ asmlinkage void __init xen_start_kernel(void)
 	have_vcpu_info_placement = 0;
 #endif
 
+	/* setup percpu state */
+	load_percpu_segment(0);
+
 	xen_smp_init();
 
 	/* Get mfn list */

arch/x86/xen/smp.c

@@ -170,7 +170,8 @@ static void __init xen_smp_prepare_boot_cpu(void)
 
 	/* We've switched to the "real" per-cpu gdt, so make sure the
 	   old memory can be recycled */
-	make_lowmem_page_readwrite(&per_cpu_var(gdt_page));
+	make_lowmem_page_readwrite(__per_cpu_load +
+				   (unsigned long)&per_cpu_var(gdt_page));
 
 	xen_setup_vcpu_info_placement();
 }
@@ -235,6 +236,8 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
 	ctxt->user_regs.ss = __KERNEL_DS;
 #ifdef CONFIG_X86_32
 	ctxt->user_regs.fs = __KERNEL_PERCPU;
+#else
+	ctxt->gs_base_kernel = per_cpu_offset(cpu);
 #endif
 	ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
 	ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */

block/blk-barrier.c

@@ -302,7 +302,7 @@ static void bio_end_empty_barrier(struct bio *bio, int err)
  * Description:
  *    Issue a flush for the block device in question. Caller can supply
  *    room for storing the error offset in case of a flush error, if they
- *    wish to.  Caller must run wait_for_completion() on its own.
+ *    wish to.
  */
 int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
 {

block/blk-core.c

@@ -64,11 +64,12 @@ static struct workqueue_struct *kblockd_workqueue;
 
 static void drive_stat_acct(struct request *rq, int new_io)
 {
+	struct gendisk *disk = rq->rq_disk;
 	struct hd_struct *part;
 	int rw = rq_data_dir(rq);
 	int cpu;
 
-	if (!blk_fs_request(rq) || !rq->rq_disk)
+	if (!blk_fs_request(rq) || !disk || !blk_queue_io_stat(disk->queue))
 		return;
 
 	cpu = part_stat_lock();
@@ -599,8 +600,7 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 	q->request_fn		= rfn;
 	q->prep_rq_fn		= NULL;
 	q->unplug_fn		= generic_unplug_device;
-	q->queue_flags		= (1 << QUEUE_FLAG_CLUSTER |
-				   1 << QUEUE_FLAG_STACKABLE);
+	q->queue_flags		= QUEUE_FLAG_DEFAULT;
 	q->queue_lock		= lock;
 
 	blk_queue_segment_boundary(q, BLK_SEG_BOUNDARY_MASK);
@@ -1125,6 +1125,8 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 
 	if (bio_sync(bio))
 		req->cmd_flags |= REQ_RW_SYNC;
+	if (bio_unplug(bio))
+		req->cmd_flags |= REQ_UNPLUG;
 	if (bio_rw_meta(bio))
 		req->cmd_flags |= REQ_RW_META;
 
@@ -1141,6 +1143,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	int el_ret, nr_sectors;
 	const unsigned short prio = bio_prio(bio);
 	const int sync = bio_sync(bio);
+	const int unplug = bio_unplug(bio);
 	int rw_flags;
 
 	nr_sectors = bio_sectors(bio);
@@ -1244,7 +1247,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 		blk_plug_device(q);
 	add_request(q, req);
 out:
-	if (sync || blk_queue_nonrot(q))
+	if (unplug || blk_queue_nonrot(q))
 		__generic_unplug_device(q);
 	spin_unlock_irq(q->queue_lock);
 	return 0;
@@ -1448,6 +1451,11 @@ static inline void __generic_make_request(struct bio *bio)
 			err = -EOPNOTSUPP;
 			goto end_io;
 		}
+		if (bio_barrier(bio) && bio_has_data(bio) &&
+		    (q->next_ordered == QUEUE_ORDERED_NONE)) {
+			err = -EOPNOTSUPP;
+			goto end_io;
+		}
 
 		ret = q->make_request_fn(q, bio);
 	} while (ret);
@@ -1655,6 +1663,55 @@ void blkdev_dequeue_request(struct request *req)
 }
 EXPORT_SYMBOL(blkdev_dequeue_request);
 
+static void blk_account_io_completion(struct request *req, unsigned int bytes)
+{
+	struct gendisk *disk = req->rq_disk;
+
+	if (!disk || !blk_queue_io_stat(disk->queue))
+		return;
+
+	if (blk_fs_request(req)) {
+		const int rw = rq_data_dir(req);
+		struct hd_struct *part;
+		int cpu;
+
+		cpu = part_stat_lock();
+		part = disk_map_sector_rcu(req->rq_disk, req->sector);
+		part_stat_add(cpu, part, sectors[rw], bytes >> 9);
+		part_stat_unlock();
+	}
+}
+
+static void blk_account_io_done(struct request *req)
+{
+	struct gendisk *disk = req->rq_disk;
+
+	if (!disk || !blk_queue_io_stat(disk->queue))
+		return;
+
+	/*
+	 * Account IO completion.  bar_rq isn't accounted as a normal
+	 * IO on queueing nor completion.  Accounting the containing
+	 * request is enough.
+	 */
+	if (blk_fs_request(req) && req != &req->q->bar_rq) {
+		unsigned long duration = jiffies - req->start_time;
+		const int rw = rq_data_dir(req);
+		struct hd_struct *part;
+		int cpu;
+
+		cpu = part_stat_lock();
+		part = disk_map_sector_rcu(disk, req->sector);
+
+		part_stat_inc(cpu, part, ios[rw]);
+		part_stat_add(cpu, part, ticks[rw], duration);
+		part_round_stats(cpu, part);
+		part_dec_in_flight(part);
+
+		part_stat_unlock();
+	}
+}
+
 /**
  * __end_that_request_first - end I/O on a request
  * @req:      the request being processed
@@ -1690,16 +1747,7 @@ static int __end_that_request_first(struct request *req, int error,
 				(unsigned long long)req->sector);
 	}
 
-	if (blk_fs_request(req) && req->rq_disk) {
-		const int rw = rq_data_dir(req);
-		struct hd_struct *part;
-		int cpu;
-
-		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(req->rq_disk, req->sector);
-		part_stat_add(cpu, part, sectors[rw], nr_bytes >> 9);
-		part_stat_unlock();
-	}
+	blk_account_io_completion(req, nr_bytes);
 
 	total_bytes = bio_nbytes = 0;
 	while ((bio = req->bio) != NULL) {
@@ -1779,8 +1827,6 @@ static int __end_that_request_first(struct request *req, int error,
  */
 static void end_that_request_last(struct request *req, int error)
 {
-	struct gendisk *disk = req->rq_disk;
-
 	if (blk_rq_tagged(req))
 		blk_queue_end_tag(req->q, req);
 
@@ -1792,27 +1838,7 @@ static void end_that_request_last(struct request *req, int error)
 
 	blk_delete_timer(req);
 
-	/*
-	 * Account IO completion.  bar_rq isn't accounted as a normal
-	 * IO on queueing nor completion.  Accounting the containing
-	 * request is enough.
-	 */
-	if (disk && blk_fs_request(req) && req != &req->q->bar_rq) {
-		unsigned long duration = jiffies - req->start_time;
-		const int rw = rq_data_dir(req);
-		struct hd_struct *part;
-		int cpu;
-
-		cpu = part_stat_lock();
-		part = disk_map_sector_rcu(disk, req->sector);
-
-		part_stat_inc(cpu, part, ios[rw]);
-		part_stat_add(cpu, part, ticks[rw], duration);
-		part_round_stats(cpu, part);
-		part_dec_in_flight(part);
-
-		part_stat_unlock();
-	}
+	blk_account_io_done(req);
 
 	if (req->end_io)
 		req->end_io(req, error);

block/blk-integrity.c

@@ -309,24 +309,24 @@ static struct kobj_type integrity_ktype = {
 /**
  * blk_integrity_register - Register a gendisk as being integrity-capable
  * @disk:	struct gendisk pointer to make integrity-aware
- * @template:	integrity profile
+ * @template:	optional integrity profile to register
  *
  * Description: When a device needs to advertise itself as being able
  * to send/receive integrity metadata it must use this function to
  * register the capability with the block layer.  The template is a
  * blk_integrity struct with values appropriate for the underlying
- * hardware.  See Documentation/block/data-integrity.txt.
+ * hardware.  If template is NULL the new profile is allocated but
+ * not filled out. See Documentation/block/data-integrity.txt.
  */
 int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
 {
 	struct blk_integrity *bi;
 
 	BUG_ON(disk == NULL);
-	BUG_ON(template == NULL);
 
 	if (disk->integrity == NULL) {
 		bi = kmem_cache_alloc(integrity_cachep,
-						GFP_KERNEL | __GFP_ZERO);
+				      GFP_KERNEL | __GFP_ZERO);
 		if (!bi)
 			return -1;
 
@@ -346,13 +346,16 @@ int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
 		bi = disk->integrity;
 
 	/* Use the provided profile as template */
-	bi->name = template->name;
-	bi->generate_fn = template->generate_fn;
-	bi->verify_fn = template->verify_fn;
-	bi->tuple_size = template->tuple_size;
-	bi->set_tag_fn = template->set_tag_fn;
-	bi->get_tag_fn = template->get_tag_fn;
-	bi->tag_size = template->tag_size;
+	if (template != NULL) {
+		bi->name = template->name;
+		bi->generate_fn = template->generate_fn;
+		bi->verify_fn = template->verify_fn;
+		bi->tuple_size = template->tuple_size;
+		bi->set_tag_fn = template->set_tag_fn;
+		bi->get_tag_fn = template->get_tag_fn;
+		bi->tag_size = template->tag_size;
+	} else
+		bi->name = "unsupported";
 
 	return 0;
 }

block/blk-sysfs.c

@@ -130,6 +130,27 @@ static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
 	return queue_var_show(max_hw_sectors_kb, (page));
 }
 
+static ssize_t queue_nonrot_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(!blk_queue_nonrot(q), page);
+}
+
+static ssize_t queue_nonrot_store(struct request_queue *q, const char *page,
+				  size_t count)
+{
+	unsigned long nm;
+	ssize_t ret = queue_var_store(&nm, page, count);
+
+	spin_lock_irq(q->queue_lock);
+	if (nm)
+		queue_flag_clear(QUEUE_FLAG_NONROT, q);
+	else
+		queue_flag_set(QUEUE_FLAG_NONROT, q);
+	spin_unlock_irq(q->queue_lock);
+
+	return ret;
+}
+
 static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(blk_queue_nomerges(q), page);
@@ -146,8 +167,8 @@ static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
 		queue_flag_set(QUEUE_FLAG_NOMERGES, q);
 	else
 		queue_flag_clear(QUEUE_FLAG_NOMERGES, q);
-
 	spin_unlock_irq(q->queue_lock);
+
 	return ret;
 }
 
@@ -176,6 +197,27 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
 	return ret;
 }
 
+static ssize_t queue_iostats_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(blk_queue_io_stat(q), page);
+}
+
+static ssize_t queue_iostats_store(struct request_queue *q, const char *page,
+				   size_t count)
+{
+	unsigned long stats;
+	ssize_t ret = queue_var_store(&stats, page, count);
+
+	spin_lock_irq(q->queue_lock);
+	if (stats)
+		queue_flag_set(QUEUE_FLAG_IO_STAT, q);
+	else
+		queue_flag_clear(QUEUE_FLAG_IO_STAT, q);
+	spin_unlock_irq(q->queue_lock);
+
+	return ret;
+}
+
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_requests_show,
@@ -210,6 +252,12 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = {
 	.show = queue_hw_sector_size_show,
 };
 
+static struct queue_sysfs_entry queue_nonrot_entry = {
+	.attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_nonrot_show,
+	.store = queue_nonrot_store,
+};
+
 static struct queue_sysfs_entry queue_nomerges_entry = {
 	.attr = {.name = "nomerges", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_nomerges_show,
@@ -222,6 +270,12 @@ static struct queue_sysfs_entry queue_rq_affinity_entry = {
 	.store = queue_rq_affinity_store,
 };
 
+static struct queue_sysfs_entry queue_iostats_entry = {
+	.attr = {.name = "iostats", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_iostats_show,
+	.store = queue_iostats_store,
+};
+
 static struct attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -229,8 +283,10 @@ static struct attribute *default_attrs[] = {
 	&queue_max_sectors_entry.attr,
 	&queue_iosched_entry.attr,
 	&queue_hw_sector_size_entry.attr,
+	&queue_nonrot_entry.attr,
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
+	&queue_iostats_entry.attr,
 	NULL,
 };
 

block/blktrace.c

@@ -187,59 +187,12 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 
 static struct dentry *blk_tree_root;
 static DEFINE_MUTEX(blk_tree_mutex);
-static unsigned int root_users;
-
-static inline void blk_remove_root(void)
-{
-	if (blk_tree_root) {
-		debugfs_remove(blk_tree_root);
-		blk_tree_root = NULL;
-	}
-}
-
-static void blk_remove_tree(struct dentry *dir)
-{
-	mutex_lock(&blk_tree_mutex);
-	debugfs_remove(dir);
-	if (--root_users == 0)
-		blk_remove_root();
-	mutex_unlock(&blk_tree_mutex);
-}
-
-static struct dentry *blk_create_tree(const char *blk_name)
-{
-	struct dentry *dir = NULL;
-	int created = 0;
-
-	mutex_lock(&blk_tree_mutex);
-
-	if (!blk_tree_root) {
-		blk_tree_root = debugfs_create_dir("block", NULL);
-		if (!blk_tree_root)
-			goto err;
-		created = 1;
-	}
-
-	dir = debugfs_create_dir(blk_name, blk_tree_root);
-	if (dir)
-		root_users++;
-	else {
-		/* Delete root only if we created it */
-		if (created)
-			blk_remove_root();
-	}
-
-err:
-	mutex_unlock(&blk_tree_mutex);
-	return dir;
-}
 
 static void blk_trace_cleanup(struct blk_trace *bt)
 {
-	relay_close(bt->rchan);
 	debugfs_remove(bt->msg_file);
 	debugfs_remove(bt->dropped_file);
-	blk_remove_tree(bt->dir);
+	relay_close(bt->rchan);
 	free_percpu(bt->sequence);
 	free_percpu(bt->msg_data);
 	kfree(bt);
@@ -346,7 +299,18 @@ static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
 
 static int blk_remove_buf_file_callback(struct dentry *dentry)
 {
+	struct dentry *parent = dentry->d_parent;
 	debugfs_remove(dentry);
+
+	/*
+	* this will fail for all but the last file, but that is ok. what we
+	* care about is the top level buts->name directory going away, when
+	* the last trace file is gone. Then we don't have to rmdir() that
+	* manually on trace stop, so it nicely solves the issue with
+	* force killing of running traces.
+	*/
+
+	debugfs_remove(parent);
 	return 0;
 }
 
@@ -404,7 +368,15 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 		goto err;
 
 	ret = -ENOENT;
-	dir = blk_create_tree(buts->name);
+
+	if (!blk_tree_root) {
+		blk_tree_root = debugfs_create_dir("block", NULL);
+		if (!blk_tree_root)
+			return -ENOMEM;
+	}
+
+	dir = debugfs_create_dir(buts->name, blk_tree_root);
+
 	if (!dir)
 		goto err;
 
@@ -458,8 +430,6 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	atomic_dec(&blk_probes_ref);
 	mutex_unlock(&blk_probe_mutex);
 err:
-	if (dir)
-		blk_remove_tree(dir);
 	if (bt) {
 		if (bt->msg_file)
 			debugfs_remove(bt->msg_file);

block/cfq-iosched.c

@@ -84,6 +84,11 @@ struct cfq_data {
 	 */
 	struct cfq_rb_root service_tree;
 	unsigned int busy_queues;
+	/*
+	 * Used to track any pending rt requests so we can pre-empt current
+	 * non-RT cfqq in service when this value is non-zero.
+	 */
+	unsigned int busy_rt_queues;
 
 	int rq_in_driver;
 	int sync_flight;
@@ -562,6 +567,8 @@ static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	BUG_ON(cfq_cfqq_on_rr(cfqq));
 	cfq_mark_cfqq_on_rr(cfqq);
 	cfqd->busy_queues++;
+	if (cfq_class_rt(cfqq))
+		cfqd->busy_rt_queues++;
 
 	cfq_resort_rr_list(cfqd, cfqq);
 }
@@ -581,6 +588,8 @@ static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 
 	BUG_ON(!cfqd->busy_queues);
 	cfqd->busy_queues--;
+	if (cfq_class_rt(cfqq))
+		cfqd->busy_rt_queues--;
 }
 
 /*
@@ -1004,6 +1013,20 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 	if (cfq_slice_used(cfqq))
 		goto expire;
 
+	/*
+	 * If we have a RT cfqq waiting, then we pre-empt the current non-rt
+	 * cfqq.
+	 */
+	if (!cfq_class_rt(cfqq) && cfqd->busy_rt_queues) {
+		/*
+		 * We simulate this as cfqq timed out so that it gets to bank
+		 * the remaining of its time slice.
+		 */
+		cfq_log_cfqq(cfqd, cfqq, "preempt");
+		cfq_slice_expired(cfqd, 1);
+		goto new_queue;
+	}
+
 	/*
 	 * The active queue has requests and isn't expired, allow it to
 	 * dispatch.
@@ -1067,6 +1090,13 @@ __cfq_dispatch_requests(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		if (RB_EMPTY_ROOT(&cfqq->sort_list))
 			break;
 
+		/*
+		 * If there is a non-empty RT cfqq waiting for current
+		 * cfqq's timeslice to complete, pre-empt this cfqq
+		 */
+		if (!cfq_class_rt(cfqq) && cfqd->busy_rt_queues)
+			break;
+
 	} while (dispatched < max_dispatch);
 
 	/*
@@ -1801,6 +1831,12 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	if (rq_is_meta(rq) && !cfqq->meta_pending)
 		return 1;
 
+	/*
+	 * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
+	 */
+	if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
+		return 1;
+
 	if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
 		return 0;
 
@@ -1870,7 +1906,8 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		/*
 		 * not the active queue - expire current slice if it is
 		 * idle and has expired it's mean thinktime or this new queue
-		 * has some old slice time left and is of higher priority
+		 * has some old slice time left and is of higher priority or
+		 * this new queue is RT and the current one is BE
 		 */
 		cfq_preempt_queue(cfqd, cfqq);
 		cfq_mark_cfqq_must_dispatch(cfqq);

drivers/net/e1000/e1000_main.c

@@ -31,7 +31,7 @@
 
 char e1000_driver_name[] = "e1000";
 static char e1000_driver_string[] = "Intel(R) PRO/1000 Network Driver";
-#define DRV_VERSION "7.3.20-k3-NAPI"
+#define DRV_VERSION "7.3.21-k3-NAPI"
 const char e1000_driver_version[] = DRV_VERSION;
 static const char e1000_copyright[] = "Copyright (c) 1999-2006 Intel Corporation.";
 
@@ -3712,7 +3712,7 @@ static irqreturn_t e1000_intr(int irq, void *data)
 	struct e1000_hw *hw = &adapter->hw;
 	u32 rctl, icr = er32(ICR);
 
-	if (unlikely(!icr))
+	if (unlikely((!icr) || test_bit(__E1000_RESETTING, &adapter->flags)))
 		return IRQ_NONE;  /* Not our interrupt */
 
 	/* IMS will not auto-mask if INT_ASSERTED is not set, and if it is

drivers/net/gianfar_mii.c

@@ -234,6 +234,8 @@ static int gfar_mdio_probe(struct of_device *ofdev,
 	if (NULL == new_bus)
 		return -ENOMEM;
 
+	device_init_wakeup(&ofdev->dev, 1);
+
 	new_bus->name = "Gianfar MII Bus",
 	new_bus->read = &gfar_mdio_read,
 	new_bus->write = &gfar_mdio_write,

drivers/net/netxen/netxen_nic.h

@@ -210,7 +210,7 @@
 #define MAX_CMD_DESCRIPTORS_HOST	1024
 #define MAX_RCV_DESCRIPTORS_1G		2048
 #define MAX_RCV_DESCRIPTORS_10G		4096
-#define MAX_JUMBO_RCV_DESCRIPTORS	512
+#define MAX_JUMBO_RCV_DESCRIPTORS	1024
 #define MAX_LRO_RCV_DESCRIPTORS		8
 #define MAX_RCVSTATUS_DESCRIPTORS	MAX_RCV_DESCRIPTORS
 #define MAX_JUMBO_RCV_DESC	MAX_JUMBO_RCV_DESCRIPTORS

drivers/net/netxen/netxen_nic_init.c

@@ -947,8 +947,10 @@ int netxen_pinit_from_rom(struct netxen_adapter *adapter, int verbose)
 	}
 	for (i = 0; i < n; i++) {
 		if (netxen_rom_fast_read(adapter, 8*i + 4*offset, &val) != 0 ||
-		netxen_rom_fast_read(adapter, 8*i + 4*offset + 4, &addr) != 0)
+		netxen_rom_fast_read(adapter, 8*i + 4*offset + 4, &addr) != 0) {
+			kfree(buf);
 			return -EIO;
+		}
 
 		buf[i].addr = addr;
 		buf[i].data = val;

drivers/net/r6040.c

@@ -438,7 +438,6 @@ static void r6040_down(struct net_device *dev)
 {
 	struct r6040_private *lp = netdev_priv(dev);
 	void __iomem *ioaddr = lp->base;
-	struct pci_dev *pdev = lp->pdev;
 	int limit = 2048;
 	u16 *adrp;
 	u16 cmd;

drivers/net/skfp/skfddi.c

@@ -1003,9 +1003,9 @@ static int skfp_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		break;
 	case SKFP_CLR_STATS:	/* Zero out the driver statistics */
 		if (!capable(CAP_NET_ADMIN)) {
-			memset(&lp->MacStat, 0, sizeof(lp->MacStat));
-		} else {
 			status = -EPERM;
+		} else {
+			memset(&lp->MacStat, 0, sizeof(lp->MacStat));
 		}
 		break;
 	default:

drivers/net/smsc911x.c

@@ -953,7 +953,7 @@ smsc911x_rx_fastforward(struct smsc911x_data *pdata, unsigned int pktbytes)
 		do {
 			udelay(1);
 			val = smsc911x_reg_read(pdata, RX_DP_CTRL);
-		} while (timeout-- && (val & RX_DP_CTRL_RX_FFWD_));
+		} while (--timeout && (val & RX_DP_CTRL_RX_FFWD_));
 
 		if (unlikely(timeout == 0))
 			SMSC_WARNING(HW, "Timed out waiting for "

drivers/net/smsc9420.c

@@ -1378,6 +1378,7 @@ static int smsc9420_open(struct net_device *dev)
 
 	/* test the IRQ connection to the ISR */
 	smsc_dbg(IFUP, "Testing ISR using IRQ %d", dev->irq);
+	pd->software_irq_signal = false;
 
 	spin_lock_irqsave(&pd->int_lock, flags);
 	/* configure interrupt deassertion timer and enable interrupts */
@@ -1393,8 +1394,6 @@ static int smsc9420_open(struct net_device *dev)
 	smsc9420_pci_flush_write(pd);
 
 	timeout = 1000;
-	pd->software_irq_signal = false;
-	smp_wmb();
 	while (timeout--) {
 		if (pd->software_irq_signal)
 			break;

drivers/net/tulip/21142.c

@@ -9,6 +9,11 @@
 
 	Please refer to Documentation/DocBook/tulip-user.{pdf,ps,html}
 	for more information on this driver.
+
+	DC21143 manual "21143 PCI/CardBus 10/100Mb/s Ethernet LAN Controller
+	Hardware Reference Manual" is currently available at :
+	http://developer.intel.com/design/network/manuals/278074.htm
+
 	Please submit bugs to http://bugzilla.kernel.org/ .
 */
 
@@ -32,7 +37,11 @@ void t21142_media_task(struct work_struct *work)
 	int csr12 = ioread32(ioaddr + CSR12);
 	int next_tick = 60*HZ;
 	int new_csr6 = 0;
+	int csr14 = ioread32(ioaddr + CSR14);
 
+	/* CSR12[LS10,LS100] are not reliable during autonegotiation */
+	if ((csr14 & 0x80) && (csr12 & 0x7000) != 0x5000)
+		csr12 |= 6;
 	if (tulip_debug > 2)
 		printk(KERN_INFO"%s: 21143 negotiation status %8.8x, %s.\n",
 			   dev->name, csr12, medianame[dev->if_port]);
@@ -76,7 +85,7 @@ void t21142_media_task(struct work_struct *work)
 			new_csr6 = 0x83860000;
 			dev->if_port = 3;
 			iowrite32(0, ioaddr + CSR13);
-			iowrite32(0x0003FF7F, ioaddr + CSR14);
+			iowrite32(0x0003FFFF, ioaddr + CSR14);
 			iowrite16(8, ioaddr + CSR15);
 			iowrite32(1, ioaddr + CSR13);
 		}
@@ -132,10 +141,14 @@ void t21142_lnk_change(struct net_device *dev, int csr5)
 	struct tulip_private *tp = netdev_priv(dev);
 	void __iomem *ioaddr = tp->base_addr;
 	int csr12 = ioread32(ioaddr + CSR12);
+	int csr14 = ioread32(ioaddr + CSR14);
 
+	/* CSR12[LS10,LS100] are not reliable during autonegotiation */
+	if ((csr14 & 0x80) && (csr12 & 0x7000) != 0x5000)
+		csr12 |= 6;
 	if (tulip_debug > 1)
 		printk(KERN_INFO"%s: 21143 link status interrupt %8.8x, CSR5 %x, "
-			   "%8.8x.\n", dev->name, csr12, csr5, ioread32(ioaddr + CSR14));
+			   "%8.8x.\n", dev->name, csr12, csr5, csr14);
 
 	/* If NWay finished and we have a negotiated partner capability. */
 	if (tp->nway  &&  !tp->nwayset  &&  (csr12 & 0x7000) == 0x5000) {
@@ -143,7 +156,9 @@ void t21142_lnk_change(struct net_device *dev, int csr5)
 		int negotiated = tp->sym_advertise & (csr12 >> 16);
 		tp->lpar = csr12 >> 16;
 		tp->nwayset = 1;
-		if (negotiated & 0x0100)		dev->if_port = 5;
+		/* If partner cannot negotiate, it is 10Mbps Half Duplex */
+		if (!(csr12 & 0x8000))		dev->if_port = 0;
+		else if (negotiated & 0x0100)	dev->if_port = 5;
 		else if (negotiated & 0x0080)	dev->if_port = 3;
 		else if (negotiated & 0x0040)	dev->if_port = 4;
 		else if (negotiated & 0x0020)	dev->if_port = 0;
@@ -214,7 +229,7 @@ void t21142_lnk_change(struct net_device *dev, int csr5)
 			tp->timer.expires = RUN_AT(3*HZ);
 			add_timer(&tp->timer);
 		} else if (dev->if_port == 5)
-			iowrite32(ioread32(ioaddr + CSR14) & ~0x080, ioaddr + CSR14);
+			iowrite32(csr14 & ~0x080, ioaddr + CSR14);
 	} else if (dev->if_port == 0  ||  dev->if_port == 4) {
 		if ((csr12 & 4) == 0)
 			printk(KERN_INFO"%s: 21143 10baseT link beat good.\n",

drivers/net/ucc_geth.c

@@ -1536,6 +1536,11 @@ static void adjust_link(struct net_device *dev)
 static int init_phy(struct net_device *dev)
 {
 	struct ucc_geth_private *priv = netdev_priv(dev);
+	struct device_node *np = priv->node;
+	struct device_node *phy, *mdio;
+	const phandle *ph;
+	char bus_name[MII_BUS_ID_SIZE];
+	const unsigned int *id;
 	struct phy_device *phydev;
 	char phy_id[BUS_ID_SIZE];
 
@@ -1543,8 +1548,18 @@ static int init_phy(struct net_device *dev)
 	priv->oldspeed = 0;
 	priv->oldduplex = -1;
 
-	snprintf(phy_id, sizeof(phy_id), PHY_ID_FMT, priv->ug_info->mdio_bus,
-		 priv->ug_info->phy_address);
+	ph = of_get_property(np, "phy-handle", NULL);
+	phy = of_find_node_by_phandle(*ph);
+	mdio = of_get_parent(phy);
+
+	id = of_get_property(phy, "reg", NULL);
+
+	of_node_put(phy);
+	of_node_put(mdio);
+
+	uec_mdio_bus_name(bus_name, mdio);
+	snprintf(phy_id, sizeof(phy_id), "%s:%02x",
+                                bus_name, *id);
 
 	phydev = phy_connect(dev, phy_id, &adjust_link, 0, priv->phy_interface);
 
@@ -3748,6 +3763,7 @@ static int ucc_geth_probe(struct of_device* ofdev, const struct of_device_id *ma
 
 	ugeth->ug_info = ug_info;
 	ugeth->dev = dev;
+	ugeth->node = np;
 
 	return 0;
 }

drivers/net/ucc_geth.h

@@ -1186,6 +1186,8 @@ struct ucc_geth_private {
 	int oldspeed;
 	int oldduplex;
 	int oldlink;
+
+	struct device_node *node;
 };
 
 void uec_set_ethtool_ops(struct net_device *netdev);

drivers/net/ucc_geth_mii.c

@@ -156,7 +156,7 @@ static int uec_mdio_probe(struct of_device *ofdev, const struct of_device_id *ma
 	if (err)
 		goto reg_map_fail;
 
-	snprintf(new_bus->id, MII_BUS_ID_SIZE, "%x", res.start);
+	uec_mdio_bus_name(new_bus->id, np);
 
 	new_bus->irq = kmalloc(32 * sizeof(int), GFP_KERNEL);
 
@@ -283,3 +283,13 @@ void uec_mdio_exit(void)
 {
 	of_unregister_platform_driver(&uec_mdio_driver);
 }
+
+void uec_mdio_bus_name(char *name, struct device_node *np)
+{
+        const u32 *reg;
+
+        reg = of_get_property(np, "reg", NULL);
+
+        snprintf(name, MII_BUS_ID_SIZE, "%s@%x", np->name, reg ? *reg : 0);
+}
+

drivers/net/ucc_geth_mii.h

@@ -97,4 +97,5 @@ int uec_mdio_read(struct mii_bus *bus, int mii_id, int regnum);
 int uec_mdio_write(struct mii_bus *bus, int mii_id, int regnum, u16 value);
 int __init uec_mdio_init(void);
 void uec_mdio_exit(void);
+void uec_mdio_bus_name(char *name, struct device_node *np);
 #endif				/* __UEC_MII_H */

drivers/net/virtio_net.c

@@ -287,7 +287,7 @@ static void try_fill_recv_maxbufs(struct virtnet_info *vi)
 		skb_put(skb, MAX_PACKET_LEN);
 
 		hdr = skb_vnet_hdr(skb);
-		sg_init_one(sg, hdr, sizeof(*hdr));
+		sg_set_buf(sg, hdr, sizeof(*hdr));
 
 		if (vi->big_packets) {
 			for (i = 0; i < MAX_SKB_FRAGS; i++) {
@@ -488,9 +488,9 @@ static int xmit_skb(struct virtnet_info *vi, struct sk_buff *skb)
 
 	/* Encode metadata header at front. */
 	if (vi->mergeable_rx_bufs)
-		sg_init_one(sg, mhdr, sizeof(*mhdr));
+		sg_set_buf(sg, mhdr, sizeof(*mhdr));
 	else
-		sg_init_one(sg, hdr, sizeof(*hdr));
+		sg_set_buf(sg, hdr, sizeof(*hdr));
 
 	num = skb_to_sgvec(skb, sg+1, 0, skb->len) + 1;
 

drivers/net/wimax/i2400m/debugfs.c

@@ -234,20 +234,6 @@ struct dentry *debugfs_create_i2400m_reset(
 				   &fops_i2400m_reset);
 }
 
-/*
- * Debug levels control; see debug.h
- */
-struct d_level D_LEVEL[] = {
-	D_SUBMODULE_DEFINE(control),
-	D_SUBMODULE_DEFINE(driver),
-	D_SUBMODULE_DEFINE(debugfs),
-	D_SUBMODULE_DEFINE(fw),
-	D_SUBMODULE_DEFINE(netdev),
-	D_SUBMODULE_DEFINE(rfkill),
-	D_SUBMODULE_DEFINE(rx),
-	D_SUBMODULE_DEFINE(tx),
-};
-size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
 
 #define __debugfs_register(prefix, name, parent)			\
 do {									\

drivers/net/wimax/i2400m/driver.c

@@ -707,6 +707,22 @@ void i2400m_release(struct i2400m *i2400m)
 EXPORT_SYMBOL_GPL(i2400m_release);
 
 
+/*
+ * Debug levels control; see debug.h
+ */
+struct d_level D_LEVEL[] = {
+	D_SUBMODULE_DEFINE(control),
+	D_SUBMODULE_DEFINE(driver),
+	D_SUBMODULE_DEFINE(debugfs),
+	D_SUBMODULE_DEFINE(fw),
+	D_SUBMODULE_DEFINE(netdev),
+	D_SUBMODULE_DEFINE(rfkill),
+	D_SUBMODULE_DEFINE(rx),
+	D_SUBMODULE_DEFINE(tx),
+};
+size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
+
+
 static
 int __init i2400m_driver_init(void)
 {

drivers/net/wireless/ath5k/base.c

@@ -1028,6 +1028,8 @@ ath5k_setup_bands(struct ieee80211_hw *hw)
  * it's done by reseting the chip.  To accomplish this we must
  * first cleanup any pending DMA, then restart stuff after a la
  * ath5k_init.
+ *
+ * Called with sc->lock.
  */
 static int
 ath5k_chan_set(struct ath5k_softc *sc, struct ieee80211_channel *chan)
@@ -2814,11 +2816,17 @@ ath5k_config(struct ieee80211_hw *hw, u32 changed)
 {
 	struct ath5k_softc *sc = hw->priv;
 	struct ieee80211_conf *conf = &hw->conf;
+	int ret;
+
+	mutex_lock(&sc->lock);
 
 	sc->bintval = conf->beacon_int;
 	sc->power_level = conf->power_level;
 
-	return ath5k_chan_set(sc, conf->channel);
+	ret = ath5k_chan_set(sc, conf->channel);
+
+	mutex_unlock(&sc->lock);
+	return ret;
 }
 
 static int

drivers/net/wireless/iwlwifi/iwl-agn.c

@@ -1719,6 +1719,10 @@ static int iwl_read_ucode(struct iwl_priv *priv)
 	priv->ucode_data_backup.len = data_size;
 	iwl_alloc_fw_desc(priv->pci_dev, &priv->ucode_data_backup);
 
+	if (!priv->ucode_code.v_addr || !priv->ucode_data.v_addr ||
+	    !priv->ucode_data_backup.v_addr)
+		goto err_pci_alloc;
+
 	/* Initialization instructions and data */
 	if (init_size && init_data_size) {
 		priv->ucode_init.len = init_size;

drivers/net/wireless/rtl818x/rtl8187_rtl8225.c

@@ -285,7 +285,10 @@ static void rtl8225_rf_set_tx_power(struct ieee80211_hw *dev, int channel)
 	ofdm_power = priv->channels[channel - 1].hw_value >> 4;
 
 	cck_power = min(cck_power, (u8)11);
-	ofdm_power = min(ofdm_power, (u8)35);
+	if (ofdm_power > (u8)15)
+		ofdm_power = 25;
+	else
+		ofdm_power += 10;
 
 	rtl818x_iowrite8(priv, &priv->map->TX_GAIN_CCK,
 			 rtl8225_tx_gain_cck_ofdm[cck_power / 6] >> 1);
@@ -536,7 +539,10 @@ static void rtl8225z2_rf_set_tx_power(struct ieee80211_hw *dev, int channel)
 	cck_power += priv->txpwr_base & 0xF;
 	cck_power = min(cck_power, (u8)35);
 
-	ofdm_power = min(ofdm_power, (u8)15);
+	if (ofdm_power > (u8)15)
+		ofdm_power = 25;
+	else
+		ofdm_power += 10;
 	ofdm_power += priv->txpwr_base >> 4;
 	ofdm_power = min(ofdm_power, (u8)35);
 

drivers/serial/jsm/jsm_tty.c

@@ -161,6 +161,11 @@ static void jsm_tty_stop_rx(struct uart_port *port)
 	channel->ch_bd->bd_ops->disable_receiver(channel);
 }
 
+static void jsm_tty_enable_ms(struct uart_port *port)
+{
+	/* Nothing needed */
+}
+
 static void jsm_tty_break(struct uart_port *port, int break_state)
 {
 	unsigned long lock_flags;
@@ -345,6 +350,7 @@ static struct uart_ops jsm_ops = {
 	.start_tx	= jsm_tty_start_tx,
 	.send_xchar	= jsm_tty_send_xchar,
 	.stop_rx	= jsm_tty_stop_rx,
+	.enable_ms	= jsm_tty_enable_ms,
 	.break_ctl	= jsm_tty_break,
 	.startup	= jsm_tty_open,
 	.shutdown	= jsm_tty_close,

fs/bio-integrity.c

@@ -140,7 +140,6 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 
 	iv = bip_vec_idx(bip, bip->bip_vcnt);
 	BUG_ON(iv == NULL);
-	BUG_ON(iv->bv_page != NULL);
 
 	iv->bv_page = page;
 	iv->bv_len = len;
@@ -465,7 +464,7 @@ static int bio_integrity_verify(struct bio *bio)
 
 		if (ret) {
 			kunmap_atomic(kaddr, KM_USER0);
-			break;
+			return ret;
 		}
 
 		sectors = bv->bv_len / bi->sector_size;
@@ -493,18 +492,13 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 	struct bio_integrity_payload *bip =
 		container_of(work, struct bio_integrity_payload, bip_work);
 	struct bio *bio = bip->bip_bio;
-	int error = bip->bip_error;
+	int error;
 
-	if (bio_integrity_verify(bio)) {
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-		error = -EIO;
-	}
+	error = bio_integrity_verify(bio);
 
 	/* Restore original bio completion handler */
 	bio->bi_end_io = bip->bip_end_io;
-
-	if (bio->bi_end_io)
-		bio->bi_end_io(bio, error);
+	bio_endio(bio, error);
 }
 
 /**
@@ -525,7 +519,17 @@ void bio_integrity_endio(struct bio *bio, int error)
 
 	BUG_ON(bip->bip_bio != bio);
 
-	bip->bip_error = error;
+	/* In case of an I/O error there is no point in verifying the
+	 * integrity metadata.  Restore original bio end_io handler
+	 * and run it.
+	 */
+	if (error) {
+		bio->bi_end_io = bip->bip_end_io;
+		bio_endio(bio, error);
+
+		return;
+	}
+
 	INIT_WORK(&bip->bip_work, bio_integrity_verify_fn);
 	queue_work(kintegrityd_wq, &bip->bip_work);
 }

fs/compat_ioctl.c

@@ -538,6 +538,7 @@ static int dev_ifsioc(unsigned int fd, unsigned int cmd, unsigned long arg)
 		 * cannot be fixed without breaking all existing apps.
 		 */
 		case TUNSETIFF:
+		case TUNGETIFF:
 		case SIOCGIFFLAGS:
 		case SIOCGIFMETRIC:
 		case SIOCGIFMTU:
@@ -1982,6 +1983,11 @@ COMPATIBLE_IOCTL(TUNSETNOCSUM)
 COMPATIBLE_IOCTL(TUNSETDEBUG)
 COMPATIBLE_IOCTL(TUNSETPERSIST)
 COMPATIBLE_IOCTL(TUNSETOWNER)
+COMPATIBLE_IOCTL(TUNSETLINK)
+COMPATIBLE_IOCTL(TUNSETGROUP)
+COMPATIBLE_IOCTL(TUNGETFEATURES)
+COMPATIBLE_IOCTL(TUNSETOFFLOAD)
+COMPATIBLE_IOCTL(TUNSETTXFILTER)
 /* Big V */
 COMPATIBLE_IOCTL(VT_SETMODE)
 COMPATIBLE_IOCTL(VT_GETMODE)
@@ -2573,6 +2579,7 @@ HANDLE_IOCTL(SIOCGIFPFLAGS, dev_ifsioc)
 HANDLE_IOCTL(SIOCGIFTXQLEN, dev_ifsioc)
 HANDLE_IOCTL(SIOCSIFTXQLEN, dev_ifsioc)
 HANDLE_IOCTL(TUNSETIFF, dev_ifsioc)
+HANDLE_IOCTL(TUNGETIFF, dev_ifsioc)
 HANDLE_IOCTL(SIOCETHTOOL, ethtool_ioctl)
 HANDLE_IOCTL(SIOCBONDENSLAVE, bond_ioctl)
 HANDLE_IOCTL(SIOCBONDRELEASE, bond_ioctl)

fs/ext3/namei.c

@@ -1358,7 +1358,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 	struct fake_dirent *fde;
 
 	blocksize =  dir->i_sb->s_blocksize;
-	dxtrace(printk("Creating index\n"));
+	dxtrace(printk(KERN_DEBUG "Creating index: inode %lu\n", dir->i_ino));
 	retval = ext3_journal_get_write_access(handle, bh);
 	if (retval) {
 		ext3_std_error(dir->i_sb, retval);
@@ -1367,6 +1367,19 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 	}
 	root = (struct dx_root *) bh->b_data;
 
+	/* The 0th block becomes the root, move the dirents out */
+	fde = &root->dotdot;
+	de = (struct ext3_dir_entry_2 *)((char *)fde +
+			ext3_rec_len_from_disk(fde->rec_len));
+	if ((char *) de >= (((char *) root) + blocksize)) {
+		ext3_error(dir->i_sb, __func__,
+			   "invalid rec_len for '..' in inode %lu",
+			   dir->i_ino);
+		brelse(bh);
+		return -EIO;
+	}
+	len = ((char *) root) + blocksize - (char *) de;
+
 	bh2 = ext3_append (handle, dir, &block, &retval);
 	if (!(bh2)) {
 		brelse(bh);
@@ -1375,11 +1388,6 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 	EXT3_I(dir)->i_flags |= EXT3_INDEX_FL;
 	data1 = bh2->b_data;
 
-	/* The 0th block becomes the root, move the dirents out */
-	fde = &root->dotdot;
-	de = (struct ext3_dir_entry_2 *)((char *)fde +
-			ext3_rec_len_from_disk(fde->rec_len));
-	len = ((char *) root) + blocksize - (char *) de;
 	memcpy (data1, de, len);
 	de = (struct ext3_dir_entry_2 *) data1;
 	top = data1 + len;

fs/ext4/balloc.c

@@ -684,15 +684,15 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb)
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		if (!gdp)
 			continue;
-		desc_count += le16_to_cpu(gdp->bg_free_blocks_count);
+		desc_count += ext4_free_blks_count(sb, gdp);
 		brelse(bitmap_bh);
 		bitmap_bh = ext4_read_block_bitmap(sb, i);
 		if (bitmap_bh == NULL)
 			continue;
 
 		x = ext4_count_free(bitmap_bh, sb->s_blocksize);
-		printk(KERN_DEBUG "group %lu: stored = %d, counted = %u\n",
-			i, le16_to_cpu(gdp->bg_free_blocks_count), x);
+		printk(KERN_DEBUG "group %u: stored = %d, counted = %u\n",
+			i, ext4_free_blks_count(sb, gdp), x);
 		bitmap_count += x;
 	}
 	brelse(bitmap_bh);

fs/ext4/ext4.h

@@ -1206,8 +1206,11 @@ static inline void ext4_r_blocks_count_set(struct ext4_super_block *es,
 
 static inline loff_t ext4_isize(struct ext4_inode *raw_inode)
 {
-	return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
-		le32_to_cpu(raw_inode->i_size_lo);
+	if (S_ISREG(le16_to_cpu(raw_inode->i_mode)))
+		return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
+			le32_to_cpu(raw_inode->i_size_lo);
+	else
+		return (loff_t) le32_to_cpu(raw_inode->i_size_lo);
 }
 
 static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size)

fs/ext4/extents.c

@@ -3048,7 +3048,7 @@ long ext4_fallocate(struct inode *inode, int mode, loff_t offset, loff_t len)
 			WARN_ON(ret <= 0);
 			printk(KERN_ERR "%s: ext4_ext_get_blocks "
 				    "returned error inode#%lu, block=%u, "
-				    "max_blocks=%lu", __func__,
+				    "max_blocks=%u", __func__,
 				    inode->i_ino, block, max_blocks);
 #endif
 			ext4_mark_inode_dirty(handle, inode);

fs/ext4/inode.c

@@ -360,9 +360,9 @@ static int ext4_block_to_path(struct inode *inode,
 		final = ptrs;
 	} else {
 		ext4_warning(inode->i_sb, "ext4_block_to_path",
-				"block %lu > max",
+				"block %lu > max in inode %lu",
 				i_block + direct_blocks +
-				indirect_blocks + double_blocks);
+				indirect_blocks + double_blocks, inode->i_ino);
 	}
 	if (boundary)
 		*boundary = final - 1 - (i_block & (ptrs - 1));
@@ -2821,9 +2821,6 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
 		filemap_write_and_wait(mapping);
 	}
 
-	BUG_ON(!EXT4_JOURNAL(inode) &&
-	       EXT4_I(inode)->i_state & EXT4_STATE_JDATA);
-
 	if (EXT4_JOURNAL(inode) && EXT4_I(inode)->i_state & EXT4_STATE_JDATA) {
 		/*
 		 * This is a REALLY heavyweight approach, but the use of
@@ -3622,7 +3619,7 @@ static void ext4_free_data(handle_t *handle, struct inode *inode,
 		 * block pointed to itself, it would have been detached when
 		 * the block was cleared. Check for this instead of OOPSing.
 		 */
-		if (bh2jh(this_bh))
+		if ((EXT4_JOURNAL(inode) == NULL) || bh2jh(this_bh))
 			ext4_handle_dirty_metadata(handle, inode, this_bh);
 		else
 			ext4_error(inode->i_sb, __func__,

fs/ext4/mballoc.c

@@ -3025,7 +3025,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 		goto out_err;
 
 	ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group,
-			gdp->bg_free_blocks_count);
+			ext4_free_blks_count(sb, gdp));
 
 	err = ext4_journal_get_write_access(handle, gdp_bh);
 	if (err)

fs/ext4/namei.c

@@ -1368,7 +1368,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 	struct fake_dirent *fde;
 
 	blocksize =  dir->i_sb->s_blocksize;
-	dxtrace(printk(KERN_DEBUG "Creating index\n"));
+	dxtrace(printk(KERN_DEBUG "Creating index: inode %lu\n", dir->i_ino));
 	retval = ext4_journal_get_write_access(handle, bh);
 	if (retval) {
 		ext4_std_error(dir->i_sb, retval);
@@ -1377,6 +1377,20 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 	}
 	root = (struct dx_root *) bh->b_data;
 
+	/* The 0th block becomes the root, move the dirents out */
+	fde = &root->dotdot;
+	de = (struct ext4_dir_entry_2 *)((char *)fde +
+		ext4_rec_len_from_disk(fde->rec_len));
+	if ((char *) de >= (((char *) root) + blocksize)) {
+		ext4_error(dir->i_sb, __func__,
+			   "invalid rec_len for '..' in inode %lu",
+			   dir->i_ino);
+		brelse(bh);
+		return -EIO;
+	}
+	len = ((char *) root) + blocksize - (char *) de;
+
+	/* Allocate new block for the 0th block's dirents */
 	bh2 = ext4_append(handle, dir, &block, &retval);
 	if (!(bh2)) {
 		brelse(bh);
@@ -1385,11 +1399,6 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 	EXT4_I(dir)->i_flags |= EXT4_INDEX_FL;
 	data1 = bh2->b_data;
 
-	/* The 0th block becomes the root, move the dirents out */
-	fde = &root->dotdot;
-	de = (struct ext4_dir_entry_2 *)((char *)fde +
-		ext4_rec_len_from_disk(fde->rec_len));
-	len = ((char *) root) + blocksize - (char *) de;
 	memcpy (data1, de, len);
 	de = (struct ext4_dir_entry_2 *) data1;
 	top = data1 + len;

fs/ext4/resize.c

@@ -861,12 +861,13 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input)
 	gdp = (struct ext4_group_desc *)((char *)primary->b_data +
 					 gdb_off * EXT4_DESC_SIZE(sb));
 
+	memset(gdp, 0, EXT4_DESC_SIZE(sb));
 	ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */
 	ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */
 	ext4_inode_table_set(sb, gdp, input->inode_table); /* LV FIXME */
 	ext4_free_blks_set(sb, gdp, input->free_blocks_count);
 	ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb));
-	gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED);
+	gdp->bg_flags = cpu_to_le16(EXT4_BG_INODE_ZEROED);
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, input->group, gdp);
 
 	/*

fs/jbd2/journal.c

@@ -37,10 +37,10 @@
 #include <linux/proc_fs.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
+#include <linux/math64.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
-#include <asm/div64.h>
 
 EXPORT_SYMBOL(jbd2_journal_start);
 EXPORT_SYMBOL(jbd2_journal_restart);
@@ -846,8 +846,8 @@ static int jbd2_seq_info_show(struct seq_file *seq, void *v)
 	    jiffies_to_msecs(s->stats->u.run.rs_flushing / s->stats->ts_tid));
 	seq_printf(seq, "  %ums logging transaction\n",
 	    jiffies_to_msecs(s->stats->u.run.rs_logging / s->stats->ts_tid));
-	seq_printf(seq, "  %luus average transaction commit time\n",
-		   do_div(s->journal->j_average_commit_time, 1000));
+	seq_printf(seq, "  %lluus average transaction commit time\n",
+		   div_u64(s->journal->j_average_commit_time, 1000));
 	seq_printf(seq, "  %lu handles per transaction\n",
 	    s->stats->u.run.rs_handle_count / s->stats->ts_tid);
 	seq_printf(seq, "  %lu blocks per transaction\n",

include/asm-generic/vmlinux.lds.h

@@ -445,10 +445,9 @@
  * section in the linker script will go there too.  @phdr should have
  * a leading colon.
  *
- * This macro defines three symbols, __per_cpu_load, __per_cpu_start
- * and __per_cpu_end.  The first one is the vaddr of loaded percpu
- * init data.  __per_cpu_start equals @vaddr and __per_cpu_end is the
- * end offset.
+ * Note that this macros defines __per_cpu_load as an absolute symbol.
+ * If there is no need to put the percpu section at a predetermined
+ * address, use PERCPU().
  */
 #define PERCPU_VADDR(vaddr, phdr)					\
 	VMLINUX_SYMBOL(__per_cpu_load) = .;				\
@@ -470,7 +469,20 @@
  * Align to @align and outputs output section for percpu area.  This
  * macro doesn't maniuplate @vaddr or @phdr and __per_cpu_load and
  * __per_cpu_start will be identical.
+ *
+ * This macro is equivalent to ALIGN(align); PERCPU_VADDR( , ) except
+ * that __per_cpu_load is defined as a relative symbol against
+ * .data.percpu which is required for relocatable x86_32
+ * configuration.
  */
 #define PERCPU(align)							\
 	. = ALIGN(align);						\
-	PERCPU_VADDR( , )
+	.data.percpu	: AT(ADDR(.data.percpu) - LOAD_OFFSET) {	\
+		VMLINUX_SYMBOL(__per_cpu_load) = .;			\
+		VMLINUX_SYMBOL(__per_cpu_start) = .;			\
+		*(.data.percpu.first)					\
+		*(.data.percpu.page_aligned)				\
+		*(.data.percpu)						\
+		*(.data.percpu.shared_aligned)				\
+		VMLINUX_SYMBOL(__per_cpu_end) = .;			\
+	}

include/linux/Kbuild

@@ -41,6 +41,7 @@ header-y += baycom.h
 header-y += bfs_fs.h
 header-y += blkpg.h
 header-y += bpqether.h
+header-y += bsg.h
 header-y += can.h
 header-y += cdk.h
 header-y += chio.h

include/linux/bio.h

@@ -144,7 +144,7 @@ struct bio {
  * bit 1 -- rw-ahead when set
  * bit 2 -- barrier
  *	Insert a serialization point in the IO queue, forcing previously
- *	submitted IO to be completed before this oen is issued.
+ *	submitted IO to be completed before this one is issued.
  * bit 3 -- synchronous I/O hint: the block layer will unplug immediately
  *	Note that this does NOT indicate that the IO itself is sync, just
  *	that the block layer will not postpone issue of this IO by plugging.
@@ -163,12 +163,33 @@ struct bio {
 #define BIO_RW		0	/* Must match RW in req flags (blkdev.h) */
 #define BIO_RW_AHEAD	1	/* Must match FAILFAST in req flags */
 #define BIO_RW_BARRIER	2
-#define BIO_RW_SYNC	3
-#define BIO_RW_META	4
-#define BIO_RW_DISCARD	5
-#define BIO_RW_FAILFAST_DEV		6
-#define BIO_RW_FAILFAST_TRANSPORT	7
-#define BIO_RW_FAILFAST_DRIVER		8
+#define BIO_RW_SYNCIO	3
+#define BIO_RW_UNPLUG	4
+#define BIO_RW_META	5
+#define BIO_RW_DISCARD	6
+#define BIO_RW_FAILFAST_DEV		7
+#define BIO_RW_FAILFAST_TRANSPORT	8
+#define BIO_RW_FAILFAST_DRIVER		9
+
+#define BIO_RW_SYNC	(BIO_RW_SYNCIO | BIO_RW_UNPLUG)
+
+#define bio_rw_flagged(bio, flag)	((bio)->bi_rw & (1 << (flag)))
+
+/*
+ * Old defines, these should eventually be replaced by direct usage of
+ * bio_rw_flagged()
+ */
+#define bio_barrier(bio)	bio_rw_flagged(bio, BIO_RW_BARRIER)
+#define bio_sync(bio)		bio_rw_flagged(bio, BIO_RW_SYNCIO)
+#define bio_unplug(bio)		bio_rw_flagged(bio, BIO_RW_UNPLUG)
+#define bio_failfast_dev(bio)	bio_rw_flagged(bio, BIO_RW_FAILFAST_DEV)
+#define bio_failfast_transport(bio)	\
+		bio_rw_flagged(bio, BIO_RW_FAILFAST_TRANSPORT)
+#define bio_failfast_driver(bio) 	\
+		bio_rw_flagged(bio, BIO_RW_FAILFAST_DRIVER)
+#define bio_rw_ahead(bio)	bio_rw_flagged(bio, BIO_RW_AHEAD)
+#define bio_rw_meta(bio)	bio_rw_flagged(bio, BIO_RW_META)
+#define bio_discard(bio)	bio_rw_flagged(bio, BIO_RW_DISCARD)
 
 /*
  * upper 16 bits of bi_rw define the io priority of this bio
@@ -193,15 +214,6 @@ struct bio {
 #define bio_offset(bio)		bio_iovec((bio))->bv_offset
 #define bio_segments(bio)	((bio)->bi_vcnt - (bio)->bi_idx)
 #define bio_sectors(bio)	((bio)->bi_size >> 9)
-#define bio_barrier(bio)	((bio)->bi_rw & (1 << BIO_RW_BARRIER))
-#define bio_sync(bio)		((bio)->bi_rw & (1 << BIO_RW_SYNC))
-#define bio_failfast_dev(bio)	((bio)->bi_rw &	(1 << BIO_RW_FAILFAST_DEV))
-#define bio_failfast_transport(bio)	\
-	((bio)->bi_rw & (1 << BIO_RW_FAILFAST_TRANSPORT))
-#define bio_failfast_driver(bio) ((bio)->bi_rw & (1 << BIO_RW_FAILFAST_DRIVER))
-#define bio_rw_ahead(bio)	((bio)->bi_rw & (1 << BIO_RW_AHEAD))
-#define bio_rw_meta(bio)	((bio)->bi_rw & (1 << BIO_RW_META))
-#define bio_discard(bio)	((bio)->bi_rw & (1 << BIO_RW_DISCARD))
 #define bio_empty_barrier(bio)	(bio_barrier(bio) && !bio_has_data(bio) && !bio_discard(bio))
 
 static inline unsigned int bio_cur_sectors(struct bio *bio)
@@ -312,7 +324,6 @@ struct bio_integrity_payload {
 	void			*bip_buf;	/* generated integrity data */
 	bio_end_io_t		*bip_end_io;	/* saved I/O completion fn */
 
-	int			bip_error;	/* saved I/O error */
 	unsigned int		bip_size;
 
 	unsigned short		bip_pool;	/* pool the ivec came from */

include/linux/blkdev.h

@@ -108,6 +108,7 @@ enum rq_flag_bits {
 	__REQ_RW_META,		/* metadata io request */
 	__REQ_COPY_USER,	/* contains copies of user pages */
 	__REQ_INTEGRITY,	/* integrity metadata has been remapped */
+	__REQ_UNPLUG,		/* unplug queue on submission */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -134,6 +135,7 @@ enum rq_flag_bits {
 #define REQ_RW_META	(1 << __REQ_RW_META)
 #define REQ_COPY_USER	(1 << __REQ_COPY_USER)
 #define REQ_INTEGRITY	(1 << __REQ_INTEGRITY)
+#define REQ_UNPLUG	(1 << __REQ_UNPLUG)
 
 #define BLK_MAX_CDB	16
 
@@ -449,6 +451,11 @@ struct request_queue
 #define QUEUE_FLAG_STACKABLE   13	/* supports request stacking */
 #define QUEUE_FLAG_NONROT      14	/* non-rotational device (SSD) */
 #define QUEUE_FLAG_VIRT        QUEUE_FLAG_NONROT /* paravirt device */
+#define QUEUE_FLAG_IO_STAT     15	/* do IO stats */
+
+#define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
+				 (1 << QUEUE_FLAG_CLUSTER) |		\
+				  1 << QUEUE_FLAG_STACKABLE)
 
 static inline int queue_is_locked(struct request_queue *q)
 {
@@ -565,6 +572,7 @@ enum {
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
+#define blk_queue_io_stat(q)	test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
 #define blk_queue_flushing(q)	((q)->ordseq)
 #define blk_queue_stackable(q)	\
 	test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags)

include/linux/jbd2.h

@@ -308,7 +308,8 @@ void buffer_assertion_failure(struct buffer_head *bh);
 		int val = (expr);					     \
 		if (!val) {						     \
 			printk(KERN_ERR					     \
-				"EXT3-fs unexpected failure: %s;\n",# expr); \
+			       "JBD2 unexpected failure: %s: %s;\n",	     \
+			       __func__, #expr);			     \
 			printk(KERN_ERR why "\n");			     \
 		}							     \
 		val;							     \

include/net/inet_hashtables.h

@@ -182,7 +182,7 @@ static inline int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
 		size = 2048;
 	if (nr_pcpus >= 32)
 		size = 4096;
-	if (sizeof(rwlock_t) != 0) {
+	if (sizeof(spinlock_t) != 0) {
 #ifdef CONFIG_NUMA
 		if (size * sizeof(spinlock_t) > PAGE_SIZE)
 			hashinfo->ehash_locks = vmalloc(size * sizeof(spinlock_t));

mm/mmap.c

@@ -658,6 +658,9 @@ again:			remove_next = 1 + (end > next->vm_end);
 	validate_mm(mm);
 }
 
+/* Flags that can be inherited from an existing mapping when merging */
+#define VM_MERGEABLE_FLAGS (VM_CAN_NONLINEAR)
+
 /*
  * If the vma has a ->close operation then the driver probably needs to release
  * per-vma resources, so we don't attempt to merge those.
@@ -665,7 +668,7 @@ again:			remove_next = 1 + (end > next->vm_end);
 static inline int is_mergeable_vma(struct vm_area_struct *vma,
 			struct file *file, unsigned long vm_flags)
 {
-	if (vma->vm_flags != vm_flags)
+	if ((vma->vm_flags ^ vm_flags) & ~VM_MERGEABLE_FLAGS)
 		return 0;
 	if (vma->vm_file != file)
 		return 0;

net/core/skbuff.c

@@ -2212,10 +2212,10 @@ unsigned int skb_seq_read(unsigned int consumed, const u8 **data,
 		return 0;
 
 next_skb:
-	block_limit = skb_headlen(st->cur_skb);
+	block_limit = skb_headlen(st->cur_skb) + st->stepped_offset;
 
 	if (abs_offset < block_limit) {
-		*data = st->cur_skb->data + abs_offset;
+		*data = st->cur_skb->data + (abs_offset - st->stepped_offset);
 		return block_limit - abs_offset;
 	}
 
@@ -2250,13 +2250,14 @@ unsigned int skb_seq_read(unsigned int consumed, const u8 **data,
 		st->frag_data = NULL;
 	}
 
-	if (st->cur_skb->next) {
-		st->cur_skb = st->cur_skb->next;
+	if (st->root_skb == st->cur_skb &&
+	    skb_shinfo(st->root_skb)->frag_list) {
+		st->cur_skb = skb_shinfo(st->root_skb)->frag_list;
 		st->frag_idx = 0;
 		goto next_skb;
-	} else if (st->root_skb == st->cur_skb &&
-		   skb_shinfo(st->root_skb)->frag_list) {
-		st->cur_skb = skb_shinfo(st->root_skb)->frag_list;
+	} else if (st->cur_skb->next) {
+		st->cur_skb = st->cur_skb->next;
+		st->frag_idx = 0;
 		goto next_skb;
 	}
 

net/ipv4/ipconfig.c

@@ -1268,6 +1268,9 @@ __be32 __init root_nfs_parse_addr(char *name)
 static int __init ip_auto_config(void)
 {
 	__be32 addr;
+#ifdef IPCONFIG_DYNAMIC
+	int retries = CONF_OPEN_RETRIES;
+#endif
 
 #ifdef CONFIG_PROC_FS
 	proc_net_fops_create(&init_net, "pnp", S_IRUGO, &pnp_seq_fops);
@@ -1304,9 +1307,6 @@ static int __init ip_auto_config(void)
 #endif
 	    ic_first_dev->next) {
 #ifdef IPCONFIG_DYNAMIC
-
-		int retries = CONF_OPEN_RETRIES;
-
 		if (ic_dynamic() < 0) {
 			ic_close_devs();
 

net/ipv4/tcp.c

@@ -524,7 +524,8 @@ static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
 	struct tcp_splice_state *tss = rd_desc->arg.data;
 	int ret;
 
-	ret = skb_splice_bits(skb, offset, tss->pipe, rd_desc->count, tss->flags);
+	ret = skb_splice_bits(skb, offset, tss->pipe, min(rd_desc->count, len),
+			      tss->flags);
 	if (ret > 0)
 		rd_desc->count -= ret;
 	return ret;

net/ipv4/udp.c

@@ -120,8 +120,11 @@ EXPORT_SYMBOL(sysctl_udp_wmem_min);
 atomic_t udp_memory_allocated;
 EXPORT_SYMBOL(udp_memory_allocated);
 
+#define PORTS_PER_CHAIN (65536 / UDP_HTABLE_SIZE)
+
 static int udp_lib_lport_inuse(struct net *net, __u16 num,
 			       const struct udp_hslot *hslot,
+			       unsigned long *bitmap,
 			       struct sock *sk,
 			       int (*saddr_comp)(const struct sock *sk1,
 						 const struct sock *sk2))
@@ -132,12 +135,17 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
 	sk_nulls_for_each(sk2, node, &hslot->head)
 		if (net_eq(sock_net(sk2), net)			&&
 		    sk2 != sk					&&
-		    sk2->sk_hash == num				&&
+		    (bitmap || sk2->sk_hash == num)		&&
 		    (!sk2->sk_reuse || !sk->sk_reuse)		&&
 		    (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if
 			|| sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
-		    (*saddr_comp)(sk, sk2))
-			return 1;
+		    (*saddr_comp)(sk, sk2)) {
+			if (bitmap)
+				__set_bit(sk2->sk_hash / UDP_HTABLE_SIZE,
+					  bitmap);
+			else
+				return 1;
+		}
 	return 0;
 }
 
@@ -160,32 +168,47 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 	if (!snum) {
 		int low, high, remaining;
 		unsigned rand;
-		unsigned short first;
+		unsigned short first, last;
+		DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN);
 
 		inet_get_local_port_range(&low, &high);
 		remaining = (high - low) + 1;
 
 		rand = net_random();
-		snum = first = rand % remaining + low;
-		rand |= 1;
-		for (;;) {
-			hslot = &udptable->hash[udp_hashfn(net, snum)];
+		first = (((u64)rand * remaining) >> 32) + low;
+		/*
+		 * force rand to be an odd multiple of UDP_HTABLE_SIZE
+		 */
+		rand = (rand | 1) * UDP_HTABLE_SIZE;
+		for (last = first + UDP_HTABLE_SIZE; first != last; first++) {
+			hslot = &udptable->hash[udp_hashfn(net, first)];
+			bitmap_zero(bitmap, PORTS_PER_CHAIN);
 			spin_lock_bh(&hslot->lock);
-			if (!udp_lib_lport_inuse(net, snum, hslot, sk, saddr_comp))
-				break;
-			spin_unlock_bh(&hslot->lock);
+			udp_lib_lport_inuse(net, snum, hslot, bitmap, sk,
+					    saddr_comp);
+
+			snum = first;
+			/*
+			 * Iterate on all possible values of snum for this hash.
+			 * Using steps of an odd multiple of UDP_HTABLE_SIZE
+			 * give us randomization and full range coverage.
+			 */
 			do {
-				snum = snum + rand;
-			} while (snum < low || snum > high);
-			if (snum == first)
-				goto fail;
+				if (low <= snum && snum <= high &&
+				    !test_bit(snum / UDP_HTABLE_SIZE, bitmap))
+					goto found;
+				snum += rand;
+			} while (snum != first);
+			spin_unlock_bh(&hslot->lock);
 		}
+		goto fail;
 	} else {
 		hslot = &udptable->hash[udp_hashfn(net, snum)];
 		spin_lock_bh(&hslot->lock);
-		if (udp_lib_lport_inuse(net, snum, hslot, sk, saddr_comp))
+		if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, saddr_comp))
 			goto fail_unlock;
 	}
+found:
 	inet_sk(sk)->num = snum;
 	sk->sk_hash = snum;
 	if (sk_unhashed(sk)) {

net/ipv6/addrconf.c

@@ -4250,7 +4250,7 @@ static struct addrconf_sysctl_table
 			.procname	=	"mc_forwarding",
 			.data		=	&ipv6_devconf.mc_forwarding,
 			.maxlen		=	sizeof(int),
-			.mode		=	0644,
+			.mode		=	0444,
 			.proc_handler	=	proc_dointvec,
 		},
 #endif

net/ipv6/icmp.c

@@ -443,10 +443,10 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
 	if (xfrm_decode_session_reverse(skb, &fl2, AF_INET6))
 		goto relookup_failed;
 
-	if (ip6_dst_lookup(sk, &dst2, &fl))
+	if (ip6_dst_lookup(sk, &dst2, &fl2))
 		goto relookup_failed;
 
-	err = xfrm_lookup(net, &dst2, &fl, sk, XFRM_LOOKUP_ICMP);
+	err = xfrm_lookup(net, &dst2, &fl2, sk, XFRM_LOOKUP_ICMP);
 	switch (err) {
 	case 0:
 		dst_release(dst);

net/ipv6/ip6_input.c

@@ -255,6 +255,7 @@ int ip6_mc_input(struct sk_buff *skb)
 	 *      IPv6 multicast router mode is now supported ;)
 	 */
 	if (dev_net(skb->dev)->ipv6.devconf_all->mc_forwarding &&
+	    !(ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) &&
 	    likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) {
 		/*
 		 * Okay, we try to forward - split and duplicate
@@ -316,7 +317,6 @@ int ip6_mc_input(struct sk_buff *skb)
 		}
 
 		if (skb2) {
-			skb2->dev = skb2->dst->dev;
 			ip6_mr_input(skb2);
 		}
 	}

net/ipv6/ip6mr.c

@@ -365,7 +365,9 @@ static int pim6_rcv(struct sk_buff *skb)
 	pim = (struct pimreghdr *)skb_transport_header(skb);
 	if (pim->type != ((PIM_VERSION << 4) | PIM_REGISTER) ||
 	    (pim->flags & PIM_NULL_REGISTER) ||
-	    (ip_compute_csum((void *)pim, sizeof(*pim)) != 0 &&
+	    (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
+			     sizeof(*pim), IPPROTO_PIM,
+			     csum_partial((void *)pim, sizeof(*pim), 0)) &&
 	     csum_fold(skb_checksum(skb, 0, skb->len, 0))))
 		goto drop;
 
@@ -392,7 +394,7 @@ static int pim6_rcv(struct sk_buff *skb)
 	skb_pull(skb, (u8 *)encap - skb->data);
 	skb_reset_network_header(skb);
 	skb->dev = reg_dev;
-	skb->protocol = htons(ETH_P_IP);
+	skb->protocol = htons(ETH_P_IPV6);
 	skb->ip_summed = 0;
 	skb->pkt_type = PACKET_HOST;
 	dst_release(skb->dst);
@@ -481,6 +483,7 @@ static int mif6_delete(struct net *net, int vifi)
 {
 	struct mif_device *v;
 	struct net_device *dev;
+	struct inet6_dev *in6_dev;
 	if (vifi < 0 || vifi >= net->ipv6.maxvif)
 		return -EADDRNOTAVAIL;
 
@@ -513,6 +516,10 @@ static int mif6_delete(struct net *net, int vifi)
 
 	dev_set_allmulti(dev, -1);
 
+	in6_dev = __in6_dev_get(dev);
+	if (in6_dev)
+		in6_dev->cnf.mc_forwarding--;
+
 	if (v->flags & MIFF_REGISTER)
 		unregister_netdevice(dev);
 
@@ -622,6 +629,7 @@ static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock)
 	int vifi = vifc->mif6c_mifi;
 	struct mif_device *v = &net->ipv6.vif6_table[vifi];
 	struct net_device *dev;
+	struct inet6_dev *in6_dev;
 	int err;
 
 	/* Is vif busy ? */
@@ -662,6 +670,10 @@ static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock)
 		return -EINVAL;
 	}
 
+	in6_dev = __in6_dev_get(dev);
+	if (in6_dev)
+		in6_dev->cnf.mc_forwarding++;
+
 	/*
 	 *	Fill in the VIF structures
 	 */
@@ -838,8 +850,6 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi,
 
 	skb->dst = dst_clone(pkt->dst);
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
-
-	skb_pull(skb, sizeof(struct ipv6hdr));
 	}
 
 	if (net->ipv6.mroute6_sk == NULL) {
@@ -1222,8 +1232,10 @@ static int ip6mr_sk_init(struct sock *sk)
 
 	rtnl_lock();
 	write_lock_bh(&mrt_lock);
-	if (likely(net->ipv6.mroute6_sk == NULL))
+	if (likely(net->ipv6.mroute6_sk == NULL)) {
 		net->ipv6.mroute6_sk = sk;
+		net->ipv6.devconf_all->mc_forwarding++;
+	}
 	else
 		err = -EADDRINUSE;
 	write_unlock_bh(&mrt_lock);
@@ -1242,6 +1254,7 @@ int ip6mr_sk_done(struct sock *sk)
 	if (sk == net->ipv6.mroute6_sk) {
 		write_lock_bh(&mrt_lock);
 		net->ipv6.mroute6_sk = NULL;
+		net->ipv6.devconf_all->mc_forwarding--;
 		write_unlock_bh(&mrt_lock);
 
 		mroute_clean_tables(net);

net/ipv6/route.c

@@ -794,7 +794,7 @@ void ip6_route_input(struct sk_buff *skb)
 		.proto = iph->nexthdr,
 	};
 
-	if (rt6_need_strict(&iph->daddr))
+	if (rt6_need_strict(&iph->daddr) && skb->dev->type != ARPHRD_PIMREG)
 		flags |= RT6_LOOKUP_F_IFACE;
 
 	skb->dst = fib6_rule_lookup(net, &fl, flags, ip6_pol_route_input);

net/wimax/debugfs.c

@@ -28,17 +28,6 @@
 #include "debug-levels.h"
 
 
-/* Debug framework control of debug levels */
-struct d_level D_LEVEL[] = {
-	D_SUBMODULE_DEFINE(debugfs),
-	D_SUBMODULE_DEFINE(id_table),
-	D_SUBMODULE_DEFINE(op_msg),
-	D_SUBMODULE_DEFINE(op_reset),
-	D_SUBMODULE_DEFINE(op_rfkill),
-	D_SUBMODULE_DEFINE(stack),
-};
-size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
-
 #define __debugfs_register(prefix, name, parent)			\
 do {									\
 	result = d_level_register_debugfs(prefix, name, parent);	\

net/wimax/stack.c

@@ -516,6 +516,19 @@ void wimax_dev_rm(struct wimax_dev *wimax_dev)
 }
 EXPORT_SYMBOL_GPL(wimax_dev_rm);
 
+
+/* Debug framework control of debug levels */
+struct d_level D_LEVEL[] = {
+	D_SUBMODULE_DEFINE(debugfs),
+	D_SUBMODULE_DEFINE(id_table),
+	D_SUBMODULE_DEFINE(op_msg),
+	D_SUBMODULE_DEFINE(op_reset),
+	D_SUBMODULE_DEFINE(op_rfkill),
+	D_SUBMODULE_DEFINE(stack),
+};
+size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
+
+
 struct genl_family wimax_gnl_family = {
 	.id = GENL_ID_GENERATE,
 	.name = "WiMAX",

net/wireless/reg.c

@@ -498,6 +498,7 @@ static struct ieee80211_regdomain *country_ie_2_rd(
 	 * calculate the number of reg rules we will need. We will need one
 	 * for each channel subband */
 	while (country_ie_len >= 3) {
+		int end_channel = 0;
 		struct ieee80211_country_ie_triplet *triplet =
 			(struct ieee80211_country_ie_triplet *) country_ie;
 		int cur_sub_max_channel = 0, cur_channel = 0;
@@ -509,9 +510,25 @@ static struct ieee80211_regdomain *country_ie_2_rd(
 			continue;
 		}
 
+		/* 2 GHz */
+		if (triplet->chans.first_channel <= 14)
+			end_channel = triplet->chans.first_channel +
+				triplet->chans.num_channels;
+		else
+			/*
+			 * 5 GHz -- For example in country IEs if the first
+			 * channel given is 36 and the number of channels is 4
+			 * then the individual channel numbers defined for the
+			 * 5 GHz PHY by these parameters are: 36, 40, 44, and 48
+			 * and not 36, 37, 38, 39.
+			 *
+			 * See: http://tinyurl.com/11d-clarification
+			 */
+			end_channel =  triplet->chans.first_channel +
+				(4 * (triplet->chans.num_channels - 1));
+
 		cur_channel = triplet->chans.first_channel;
-		cur_sub_max_channel = ieee80211_channel_to_frequency(
-			cur_channel + triplet->chans.num_channels);
+		cur_sub_max_channel = end_channel;
 
 		/* Basic sanity check */
 		if (cur_sub_max_channel < cur_channel)
@@ -590,15 +607,6 @@ static struct ieee80211_regdomain *country_ie_2_rd(
 			end_channel = triplet->chans.first_channel +
 				triplet->chans.num_channels;
 		else
-			/*
-			 * 5 GHz -- For example in country IEs if the first
-			 * channel given is 36 and the number of channels is 4
-			 * then the individual channel numbers defined for the
-			 * 5 GHz PHY by these parameters are: 36, 40, 44, and 48
-			 * and not 36, 37, 38, 39.
-			 *
-			 * See: http://tinyurl.com/11d-clarification
-			 */
 			end_channel =  triplet->chans.first_channel +
 				(4 * (triplet->chans.num_channels - 1));
 
@@ -1276,7 +1284,7 @@ static void reg_country_ie_process_debug(
 	if (intersected_rd) {
 		printk(KERN_DEBUG "cfg80211: We intersect both of these "
 			"and get:\n");
-		print_regdomain_info(rd);
+		print_regdomain_info(intersected_rd);
 		return;
 	}
 	printk(KERN_DEBUG "cfg80211: Intersection between both failed\n");