2.6.26-stable review

@@ -552,8 +552,31 @@ void __init setup_boot_APIC_clock(void)
 	setup_APIC_timer();
 }
 
-void __devinit setup_secondary_APIC_clock(void)
+/*
+ * AMD C1E enabled CPUs have a real nasty problem: Some BIOSes set the
+ * C1E flag only in the secondary CPU, so when we detect the wreckage
+ * we already have enabled the boot CPU local apic timer. Check, if
+ * disable_apic_timer is set and the DUMMY flag is cleared. If yes,
+ * set the DUMMY flag again and force the broadcast mode in the
+ * clockevents layer.
+ */
+static void __cpuinit check_boot_apic_timer_broadcast(void)
+{
+	if (!local_apic_timer_disabled ||
+	    (lapic_clockevent.features & CLOCK_EVT_FEAT_DUMMY))
+		return;
+
+	lapic_clockevent.features |= CLOCK_EVT_FEAT_DUMMY;
+
+	local_irq_enable();
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
+			   &boot_cpu_physical_apicid);
+	local_irq_disable();
+}
+
+void __cpuinit setup_secondary_APIC_clock(void)
 {
+	check_boot_apic_timer_broadcast();
 	setup_APIC_timer();
 }
 

@@ -70,7 +70,7 @@ static DEFINE_MUTEX(performance_mutex);
  *  0 -> cpufreq low level drivers initialized -> consider _PPC values
  *  1 -> ignore _PPC totally -> forced by user through boot param
  */
-static unsigned int ignore_ppc = -1;
+static int ignore_ppc = -1;
 module_param(ignore_ppc, uint, 0644);
 MODULE_PARM_DESC(ignore_ppc, "If the frequency of your machine gets wrongly" \
 		 "limited by BIOS, this should help");

@@ -581,8 +581,10 @@ static int __init i2c_dev_init(void)
 		goto out;
 
 	i2c_dev_class = class_create(THIS_MODULE, "i2c-dev");
-	if (IS_ERR(i2c_dev_class))
+	if (IS_ERR(i2c_dev_class)) {
+		res = PTR_ERR(i2c_dev_class);
 		goto out_unreg_chrdev;
+	}
 
 	res = i2c_add_driver(&i2cdev_driver);
 	if (res)

@@ -2258,6 +2258,12 @@ static int __devinit ixgbe_set_interrupt
 	int vector, v_budget;
 
 	/*
+	 * Set the default interrupt throttle rate.
+	 */
+	adapter->rx_eitr = (1000000 / IXGBE_DEFAULT_ITR_RX_USECS);
+	adapter->tx_eitr = (1000000 / IXGBE_DEFAULT_ITR_TX_USECS);
+
+	/*
 	 * It's easy to be greedy for MSI-X vectors, but it really
 	 * doesn't do us much good if we have a lot more vectors
 	 * than CPU's.  So let's be conservative and only ask for

@@ -103,8 +103,10 @@ static int mmc_blk_open(struct inode *in
 			check_disk_change(inode->i_bdev);
 		ret = 0;
 
-		if ((filp->f_mode & FMODE_WRITE) && md->read_only)
+		if ((filp->f_mode & FMODE_WRITE) && md->read_only) {
+			mmc_blk_put(md);
 			ret = -EROFS;
+		}
 	}
 
 	return ret;

@@ -136,7 +136,8 @@ async_tx_run_dependencies(struct dma_asy
 		spin_lock_bh(&next->lock);
 		next->parent = NULL;
 		_next = next->next;
-		next->next = NULL;
+		if (_next && _next->chan == chan)
+			next->next = NULL;
 		spin_unlock_bh(&next->lock);
 
 		next->tx_submit(next);

@@ -751,8 +751,9 @@ static inline int zonelist_node_idx(stru
  *
  * This function returns the next zone at or below a given zone index that is
  * within the allowed nodemask using a cursor as the starting point for the
- * search. The zoneref returned is a cursor that is used as the next starting
- * point for future calls to next_zones_zonelist().
+ * search. The zoneref returned is a cursor that represents the current zone
+ * being examined. It should be advanced by one before calling
+ * next_zones_zonelist again.
  */
 struct zoneref *next_zones_zonelist(struct zoneref *z,
 					enum zone_type highest_zoneidx,

@@ -768,9 +769,8 @@ struct zoneref *next_zones_zonelist(stru
  *
  * This function returns the first zone at or below a given zone index that is
  * within the allowed nodemask. The zoneref returned is a cursor that can be
- * used to iterate the zonelist with next_zones_zonelist. The cursor should
- * not be used by the caller as it does not match the value of the zone
- * returned.
+ * used to iterate the zonelist with next_zones_zonelist by advancing it by
+ * one before calling.
  */
 static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
 					enum zone_type highest_zoneidx,

@@ -795,7 +795,7 @@ static inline struct zoneref *first_zone
 #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \
 	for (z = first_zones_zonelist(zlist, highidx, nodemask, &zone);	\
 		zone;							\
-		z = next_zones_zonelist(z, highidx, nodemask, &zone))	\
+		z = next_zones_zonelist(++z, highidx, nodemask, &zone))	\
 
 /**
  * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index

@@ -69,6 +69,6 @@ struct zoneref *next_zones_zonelist(stru
 				(z->zone && !zref_in_nodemask(z, nodes)))
 			z++;
 
-	*zone = zonelist_zone(z++);
+	*zone = zonelist_zone(z);
 	return z;
 }

@@ -48,9 +48,10 @@ MODULE_ALIAS("platform:pxa2xx-spi");
 
 #define MAX_BUSES 3
 
-#define DMA_INT_MASK (DCSR_ENDINTR | DCSR_STARTINTR | DCSR_BUSERR)
-#define RESET_DMA_CHANNEL (DCSR_NODESC | DMA_INT_MASK)
-#define IS_DMA_ALIGNED(x) (((u32)(x)&0x07)==0)
+#define DMA_INT_MASK		(DCSR_ENDINTR | DCSR_STARTINTR | DCSR_BUSERR)
+#define RESET_DMA_CHANNEL	(DCSR_NODESC | DMA_INT_MASK)
+#define IS_DMA_ALIGNED(x)	(((x) & 0x07) == 0)
+#define MAX_DMA_LEN		8191
 
 /*
  * for testing SSCR1 changes that require SSP restart, basically

@@ -850,14 +851,27 @@ static void pump_transfers(unsigned long
 			udelay(previous->delay_usecs);
 	}
 
-	/* Check transfer length */
-	if (transfer->len > 8191)
-	{
-		dev_warn(&drv_data->pdev->dev, "pump_transfers: transfer "
-				"length greater than 8191\n");
-		message->status = -EINVAL;
-		giveback(drv_data);
-		return;
+	/* Check for transfers that need multiple DMA segments */
+	if (transfer->len > MAX_DMA_LEN && chip->enable_dma) {
+
+		/* reject already-mapped transfers; PIO won't always work */
+		if (message->is_dma_mapped
+				|| transfer->rx_dma || transfer->tx_dma) {
+			dev_err(&drv_data->pdev->dev,
+				"pump_transfers: mapped transfer length "
+				"of %lu is greater than %d\n",
+				transfer->len, MAX_DMA_LEN);
+			message->status = -EINVAL;
+			giveback(drv_data);
+			return;
+		}
+
+		/* warn ... we force this to PIO mode */
+		if (printk_ratelimit())
+			dev_warn(&message->spi->dev, "pump_transfers: "
+				"DMA disabled for transfer length %ld "
+				"greater than %d\n",
+				(long)drv_data->len, MAX_DMA_LEN);
 	}
 
 	/* Setup the transfer state based on the type of transfer */

@@ -926,7 +940,7 @@ static void pump_transfers(unsigned long
 							&dma_thresh))
 				if (printk_ratelimit())
 					dev_warn(&message->spi->dev,
-						"pump_transfer: "
+						"pump_transfers: "
 						"DMA burst size reduced to "
 						"match bits_per_word\n");
 		}

@@ -940,8 +954,23 @@ static void pump_transfers(unsigned long
 
 	message->state = RUNNING_STATE;
 
-	/* Try to map dma buffer and do a dma transfer if successful */
-	if ((drv_data->dma_mapped = map_dma_buffers(drv_data))) {
+	/* Try to map dma buffer and do a dma transfer if successful, but
+	 * only if the length is non-zero and less than MAX_DMA_LEN.
+	 *
+	 * Zero-length non-descriptor DMA is illegal on PXA2xx; force use
+	 * of PIO instead.  Care is needed above because the transfer may
+	 * have have been passed with buffers that are already dma mapped.
+	 * A zero-length transfer in PIO mode will not try to write/read
+	 * to/from the buffers
+	 *
+	 * REVISIT large transfers are exactly where we most want to be
+	 * using DMA.  If this happens much, split those transfers into
+	 * multiple DMA segments rather than forcing PIO.
+	 */
+	drv_data->dma_mapped = 0;
+	if (drv_data->len > 0 && drv_data->len <= MAX_DMA_LEN)
+		drv_data->dma_mapped = map_dma_buffers(drv_data);
+	if (drv_data->dma_mapped) {
 
 		/* Ensure we have the correct interrupt handler */
 		drv_data->transfer_handler = dma_transfer;

@@ -146,7 +146,6 @@ struct driver_data {
 	size_t tx_map_len;
 	u8 n_bytes;
 	u32 dma_width;
-	int cs_change;
 	int (*write)(struct driver_data *drv_data);
 	int (*read)(struct driver_data *drv_data);
 	irqreturn_t (*transfer_handler)(struct driver_data *drv_data);

@@ -408,8 +407,45 @@ static void giveback(struct driver_data 
 					struct spi_transfer,
 					transfer_list);
 
+	/* Delay if requested before any change in chip select */
+	if (last_transfer->delay_usecs)
+		udelay(last_transfer->delay_usecs);
+
+	/* Drop chip select UNLESS cs_change is true or we are returning
+	 * a message with an error, or next message is for another chip
+	 */
 	if (!last_transfer->cs_change)
 		drv_data->cs_control(PXA2XX_CS_DEASSERT);
+	else {
+		struct spi_message *next_msg;
+
+		/* Holding of cs was hinted, but we need to make sure
+		 * the next message is for the same chip.  Don't waste
+		 * time with the following tests unless this was hinted.
+		 *
+		 * We cannot postpone this until pump_messages, because
+		 * after calling msg->complete (below) the driver that
+		 * sent the current message could be unloaded, which
+		 * could invalidate the cs_control() callback...
+		 */
+
+		/* get a pointer to the next message, if any */
+		spin_lock_irqsave(&drv_data->lock, flags);
+		if (list_empty(&drv_data->queue))
+			next_msg = NULL;
+		else
+			next_msg = list_entry(drv_data->queue.next,
+					struct spi_message, queue);
+		spin_unlock_irqrestore(&drv_data->lock, flags);
+
+		/* see if the next and current messages point
+		 * to the same chip
+		 */
+		if (next_msg && next_msg->spi != msg->spi)
+			next_msg = NULL;
+		if (!next_msg || msg->state == ERROR_STATE)
+			drv_data->cs_control(PXA2XX_CS_DEASSERT);
+	}
 
 	msg->state = NULL;
 	if (msg->complete)

@@ -492,10 +528,9 @@ static void dma_transfer_complete(struct
 	msg->actual_length += drv_data->len -
 				(drv_data->rx_end - drv_data->rx);
 
-	/* Release chip select if requested, transfer delays are
-	 * handled in pump_transfers */
-	if (drv_data->cs_change)
-		drv_data->cs_control(PXA2XX_CS_DEASSERT);
+	/* Transfer delays and chip select release are
+	 * handled in pump_transfers or giveback
+	 */
 
 	/* Move to next transfer */
 	msg->state = next_transfer(drv_data);

@@ -604,10 +639,9 @@ static void int_transfer_complete(struct
 	drv_data->cur_msg->actual_length += drv_data->len -
 				(drv_data->rx_end - drv_data->rx);
 
-	/* Release chip select if requested, transfer delays are
-	 * handled in pump_transfers */
-	if (drv_data->cs_change)
-		drv_data->cs_control(PXA2XX_CS_DEASSERT);
+	/* Transfer delays and chip select release are
+	 * handled in pump_transfers or giveback
+	 */
 
 	/* Move to next transfer */
 	drv_data->cur_msg->state = next_transfer(drv_data);

@@ -842,13 +876,17 @@ static void pump_transfers(unsigned long
 		return;
 	}
 
-	/* Delay if requested at end of transfer*/
+	/* Delay if requested at end of transfer before CS change */
 	if (message->state == RUNNING_STATE) {
 		previous = list_entry(transfer->transfer_list.prev,
 					struct spi_transfer,
 					transfer_list);
 		if (previous->delay_usecs)
 			udelay(previous->delay_usecs);
+
+		/* Drop chip select only if cs_change is requested */
+		if (previous->cs_change)
+			drv_data->cs_control(PXA2XX_CS_DEASSERT);
 	}
 
 	/* Check for transfers that need multiple DMA segments */

@@ -893,7 +931,6 @@ static void pump_transfers(unsigned long
 	drv_data->len = transfer->len & DCMD_LENGTH;
 	drv_data->write = drv_data->tx ? chip->write : null_writer;
 	drv_data->read = drv_data->rx ? chip->read : null_reader;
-	drv_data->cs_change = transfer->cs_change;
 
 	/* Change speed and bit per word on a per transfer */
 	cr0 = chip->cr0;

@@ -11,7 +11,9 @@
 
 #include <linux/types.h>
 #include <linux/magic.h>
+#ifdef __KERNEL__
 #include <linux/time.h>
+#endif
 
 enum smb_protocol { 
 	SMB_PROTOCOL_NONE, 

@@ -1,6 +1,6 @@
 #include <linux/module.h>
 #include <linux/sched.h>
-#include <linux/spinlock.h>
+#include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/kprobes.h>
 #include <linux/mm.h>

@@ -279,7 +279,7 @@ struct smp_alt_module {
 	struct list_head next;
 };
 static LIST_HEAD(smp_alt_modules);
-static DEFINE_SPINLOCK(smp_alt);
+static DEFINE_MUTEX(smp_alt);
 static int smp_mode = 1;	/* protected by smp_alt */
 
 void alternatives_smp_module_add(struct module *mod, char *name,

@@ -312,12 +312,12 @@ void alternatives_smp_module_add(struct 
 		__func__, smp->locks, smp->locks_end,
 		smp->text, smp->text_end, smp->name);
 
-	spin_lock(&smp_alt);
+	mutex_lock(&smp_alt);
 	list_add_tail(&smp->next, &smp_alt_modules);
 	if (boot_cpu_has(X86_FEATURE_UP))
 		alternatives_smp_unlock(smp->locks, smp->locks_end,
 					smp->text, smp->text_end);
-	spin_unlock(&smp_alt);
+	mutex_unlock(&smp_alt);
 }
 
 void alternatives_smp_module_del(struct module *mod)

@@ -327,17 +327,17 @@ void alternatives_smp_module_del(struct 
 	if (smp_alt_once || noreplace_smp)
 		return;
 
-	spin_lock(&smp_alt);
+	mutex_lock(&smp_alt);
 	list_for_each_entry(item, &smp_alt_modules, next) {
 		if (mod != item->mod)
 			continue;
 		list_del(&item->next);
-		spin_unlock(&smp_alt);
+		mutex_unlock(&smp_alt);
 		DPRINTK("%s: %s\n", __func__, item->name);
 		kfree(item);
 		return;
 	}
-	spin_unlock(&smp_alt);
+	mutex_unlock(&smp_alt);
 }
 
 void alternatives_smp_switch(int smp)

@@ -359,7 +359,7 @@ void alternatives_smp_switch(int smp)
 		return;
 	BUG_ON(!smp && (num_online_cpus() > 1));
 
-	spin_lock(&smp_alt);
+	mutex_lock(&smp_alt);
 
 	/*
 	 * Avoid unnecessary switches because it forces JIT based VMs to

@@ -383,7 +383,7 @@ void alternatives_smp_switch(int smp)
 						mod->text, mod->text_end);
 	}
 	smp_mode = smp;
-	spin_unlock(&smp_alt);
+	mutex_unlock(&smp_alt);
 }
 
 #endif

@@ -1885,7 +1885,8 @@ int usb_add_hcd(struct usb_hcd *hcd,
 		 * with IRQF_SHARED. As usb_hcd_irq() will always disable
 		 * interrupts we can remove it here.
 		 */
-		irqflags &= ~IRQF_DISABLED;
+		if (irqflags & IRQF_SHARED)
+			irqflags &= ~IRQF_DISABLED;
 
 		snprintf(hcd->irq_descr, sizeof(hcd->irq_descr), "%s:usb%d",
 				hcd->driver->description, hcd->self.busnum);

@@ -1838,7 +1838,6 @@ clear_risc_ints:
 		WRT_REG_WORD(&reg->isp.hccr, HCCR_CLR_HOST_INT);
 	}
 	spin_unlock_irq(&ha->hardware_lock);
-	ha->isp_ops->enable_intrs(ha);
 
 fail:
 	return ret;

@@ -1740,6 +1740,8 @@ qla2x00_probe_one(struct pci_dev *pdev, 
 	if (ret)
 		goto probe_failed;
 
+	ha->isp_ops->enable_intrs(ha);
+
 	scsi_scan_host(host);
 
 	qla2x00_alloc_sysfs_attr(ha);

@@ -1667,8 +1667,8 @@ static struct snd_pci_quirk stac927x_cfg
 	/* Dell 3 stack systems with verb table in BIOS */
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL,  0x01f3, "Dell Inspiron 1420", STAC_DELL_BIOS),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL,  0x0227, "Dell Vostro 1400  ", STAC_DELL_BIOS),
-	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL,  0x022f, "Dell     ", STAC_DELL_BIOS),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL,  0x022e, "Dell     ", STAC_DELL_BIOS),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL,  0x022f, "Dell Inspiron 1525", STAC_DELL_3ST),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL,  0x0242, "Dell     ", STAC_DELL_BIOS),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL,  0x0243, "Dell     ", STAC_DELL_BIOS),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL,  0x02ff, "Dell     ", STAC_DELL_BIOS),

@@ -17,6 +17,7 @@
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
+#include <linux/delay.h>
 #include <linux/pci.h>
 #include <sound/control.h>
 #include <sound/core.h>

@@ -95,6 +96,9 @@ static void set_ak4396_params(struct oxy
 	else
 		value |= AK4396_DFS_QUAD;
 	data->ak4396_ctl2 = value;
+
+	msleep(1); /* wait for the new MCLK to become stable */
+
 	ak4396_write(chip, AK4396_CONTROL_1, AK4396_DIF_24_MSB);
 	ak4396_write(chip, AK4396_CONTROL_2, value);
 	ak4396_write(chip, AK4396_CONTROL_1, AK4396_DIF_24_MSB | AK4396_RSTN);

@@ -28,6 +28,7 @@
  * GPIO 1 -> DFS1 of AK5385
  */
 
+#include <linux/delay.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
 #include <sound/ac97_codec.h>

@@ -173,6 +174,9 @@ static void set_ak4396_params(struct oxy
 	else
 		value |= AK4396_DFS_QUAD;
 	data->ak4396_ctl2 = value;
+
+	msleep(1); /* wait for the new MCLK to become stable */
+
 	for (i = 0; i < 4; ++i) {
 		ak4396_write(chip, i,
 			     AK4396_CONTROL_1, AK4396_DIF_24_MSB);

@@ -781,7 +781,7 @@ int snd_pcm_attach_substream(struct snd_
 		return -ENODEV;
 
 	card = pcm->card;
-	down_read(&card->controls_rwsem);
+	read_lock(&card->ctl_files_rwlock);
 	list_for_each_entry(kctl, &card->ctl_files, list) {
 		if (kctl->pid == current->pid) {
 			prefer_subdevice = kctl->prefer_pcm_subdevice;

@@ -789,7 +789,7 @@ int snd_pcm_attach_substream(struct snd_
 				break;
 		}
 	}
-	up_read(&card->controls_rwsem);
+	read_unlock(&card->ctl_files_rwlock);
 
 	switch (stream) {
 	case SNDRV_PCM_STREAM_PLAYBACK:

@@ -418,7 +418,7 @@ static int snd_rawmidi_open(struct inode
 	mutex_lock(&rmidi->open_mutex);
 	while (1) {
 		subdevice = -1;
-		down_read(&card->controls_rwsem);
+		read_lock(&card->ctl_files_rwlock);
 		list_for_each_entry(kctl, &card->ctl_files, list) {
 			if (kctl->pid == current->pid) {
 				subdevice = kctl->prefer_rawmidi_subdevice;

@@ -426,7 +426,7 @@ static int snd_rawmidi_open(struct inode
 					break;
 			}
 		}
-		up_read(&card->controls_rwsem);
+		read_unlock(&card->ctl_files_rwlock);
 		err = snd_rawmidi_kernel_open(rmidi->card, rmidi->device,
 					      subdevice, fflags, rawmidi_file);
 		if (err >= 0)

@@ -1545,16 +1545,10 @@ static int snd_pcm_drop(struct snd_pcm_s
 	card = substream->pcm->card;
 
 	if (runtime->status->state == SNDRV_PCM_STATE_OPEN ||
-	    runtime->status->state == SNDRV_PCM_STATE_DISCONNECTED)
+	    runtime->status->state == SNDRV_PCM_STATE_DISCONNECTED ||
+	    runtime->status->state == SNDRV_PCM_STATE_SUSPENDED)
 		return -EBADFD;
 
-	snd_power_lock(card);
-	if (runtime->status->state == SNDRV_PCM_STATE_SUSPENDED) {
-		result = snd_power_wait(card, SNDRV_CTL_POWER_D0);
-		if (result < 0)
-			goto _unlock;
-	}
-
 	snd_pcm_stream_lock_irq(substream);
 	/* resume pause */
 	if (runtime->status->state == SNDRV_PCM_STATE_PAUSED)

@@ -1563,8 +1557,7 @@ static int snd_pcm_drop(struct snd_pcm_s
 	snd_pcm_stop(substream, SNDRV_PCM_STATE_SETUP);
 	/* runtime->control->appl_ptr = runtime->status->hw_ptr; */
 	snd_pcm_stream_unlock_irq(substream);
- _unlock:
-	snd_power_unlock(card);
+
 	return result;
 }
 

@@ -60,6 +60,7 @@ static int npt = 1;
 module_param(npt, int, S_IRUGO);
 
 static void kvm_reput_irq(struct vcpu_svm *svm);
+static void svm_flush_tlb(struct kvm_vcpu *vcpu);
 
 static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu)
 {

@@ -1017,6 +1018,15 @@ static int pf_interception(struct vcpu_s
 
 	fault_address  = svm->vmcb->control.exit_info_2;
 	error_code = svm->vmcb->control.exit_info_1;
+
+	/*
+	 * FIXME: Tis shouldn't be necessary here, but there is a flush
+	 * missing in the MMU code. Until we find this bug, flush the
+	 * complete TLB here on an NPF
+	 */
+	if (npt_enabled)
+		svm_flush_tlb(&svm->vcpu);
+
 	if (event_injection)
 		kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address);
 	return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code);

@@ -880,6 +880,10 @@ set:
 static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	unsigned long host_cr4_mce = read_cr4() & X86_CR4_MCE;
+	unsigned long old_cr4 = to_svm(vcpu)->vmcb->save.cr4;
+
+	if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE))
+		force_new_asid(vcpu);
 
 	vcpu->arch.cr4 = cr4;
 	if (!npt_enabled)

@@ -53,6 +53,59 @@ sys_sigaltstack(const stack_t __user *us
 	return do_sigaltstack(uss, uoss, regs->sp);
 }
 
+/*
+ * Signal frame handlers.
+ */
+
+static inline int save_i387(struct _fpstate __user *buf)
+{
+	struct task_struct *tsk = current;
+	int err = 0;
+
+	BUILD_BUG_ON(sizeof(struct user_i387_struct) !=
+			sizeof(tsk->thread.xstate->fxsave));
+
+	if ((unsigned long)buf % 16)
+		printk("save_i387: bad fpstate %p\n", buf);
+
+	if (!used_math())
+		return 0;
+	clear_used_math(); /* trigger finit */
+	if (task_thread_info(tsk)->status & TS_USEDFPU) {
+		err = save_i387_checking((struct i387_fxsave_struct __user *)
+					 buf);
+		if (err)
+			return err;
+		task_thread_info(tsk)->status &= ~TS_USEDFPU;
+		stts();
+	} else {
+		if (__copy_to_user(buf, &tsk->thread.xstate->fxsave,
+				   sizeof(struct i387_fxsave_struct)))
+			return -1;
+	}
+	return 1;
+}
+
+/*
+ * This restores directly out of user space. Exceptions are handled.
+ */
+static inline int restore_i387(struct _fpstate __user *buf)
+{
+	struct task_struct *tsk = current;
+	int err;
+
+	if (!used_math()) {
+		err = init_fpu(tsk);
+		if (err)
+			return err;
+	}
+
+	if (!(task_thread_info(current)->status & TS_USEDFPU)) {
+		clts();
+		task_thread_info(current)->status |= TS_USEDFPU;
+	}
+	return restore_fpu_checking((__force struct i387_fxsave_struct *)buf);
+}
 
 /*
  * Do a signal return; undo the signal stack.

60 lines not on this page · raw message

@@ -104,7 +104,16 @@ static inline int restore_i387(struct _f
 		clts();
 		task_thread_info(current)->status |= TS_USEDFPU;
 	}
-	return restore_fpu_checking((__force struct i387_fxsave_struct *)buf);
+	err = restore_fpu_checking((__force struct i387_fxsave_struct *)buf);
+	if (unlikely(err)) {
+		/*
+		 * Encountered an error while doing the restore from the
+		 * user buffer, clear the fpu state.
+		 */
+		clear_fpu(tsk);
+		clear_used_math();
+	}
+	return err;
 }
 
 /*

@@ -1141,7 +1141,14 @@ asmlinkage void math_state_restore(void)
 	}
 
 	clts();			/* Allow maths ops (or we recurse) */
-	restore_fpu_checking(&me->thread.xstate->fxsave);
+ 	/*
+ 	 * Paranoid restore. send a SIGSEGV if we fail to restore the state.
+ 	 */
+ 	if (unlikely(restore_fpu_checking(&me->thread.xstate->fxsave))) {
+ 		stts();
+ 		force_sig(SIGSEGV, me);
+ 		return;
+ 	}
 	task_thread_info(me)->status |= TS_USEDFPU;
 	me->fpu_counter++;
 }

@@ -63,8 +63,6 @@ static inline int restore_fpu_checking(s
 #else
 		     : [fx] "cdaSDb" (fx), "m" (*fx), "0" (0));
 #endif
-	if (unlikely(err))
-		init_fpu(current);
 	return err;
 }
 

@@ -234,7 +234,7 @@ static void vmi_write_ldt_entry(struct d
 				const void *desc)
 {
 	u32 *ldt_entry = (u32 *)desc;
-	vmi_ops.write_idt_entry(dt, entry, ldt_entry[0], ldt_entry[1]);
+	vmi_ops.write_ldt_entry(dt, entry, ldt_entry[0], ldt_entry[1]);
 }
 
 static void vmi_load_sp0(struct tss_struct *tss,

@@ -2868,14 +2868,17 @@ int submit_bh(int rw, struct buffer_head
 	BUG_ON(!buffer_mapped(bh));
 	BUG_ON(!bh->b_end_io);
 
-	if (buffer_ordered(bh) && (rw == WRITE))
-		rw = WRITE_BARRIER;
+	/*
+	 * Mask in barrier bit for a write (could be either a WRITE or a
+	 * WRITE_SYNC
+	 */
+	if (buffer_ordered(bh) && (rw & WRITE))
+		rw |= WRITE_BARRIER;
 
 	/*
-	 * Only clear out a write error when rewriting, should this
-	 * include WRITE_SYNC as well?
+	 * Only clear out a write error when rewriting
 	 */
-	if (test_set_buffer_req(bh) && (rw == WRITE || rw == WRITE_BARRIER))
+	if (test_set_buffer_req(bh) && (rw & WRITE))
 		clear_buffer_write_io_error(bh);
 
 	/*

@@ -332,65 +332,6 @@ int proc_pid_status(struct seq_file *m, 
 	return 0;
 }
 
-/*
- * Use precise platform statistics if available:
- */
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-static cputime_t task_utime(struct task_struct *p)
-{
-	return p->utime;
-}
-
-static cputime_t task_stime(struct task_struct *p)
-{
-	return p->stime;
-}
-#else
-static cputime_t task_utime(struct task_struct *p)
-{
-	clock_t utime = cputime_to_clock_t(p->utime),
-		total = utime + cputime_to_clock_t(p->stime);
-	u64 temp;
-
-	/*
-	 * Use CFS's precise accounting:
-	 */
-	temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);
-
-	if (total) {
-		temp *= utime;
-		do_div(temp, total);
-	}
-	utime = (clock_t)temp;
-
-	p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));
-	return p->prev_utime;
-}
-
-static cputime_t task_stime(struct task_struct *p)
-{
-	clock_t stime;
-
-	/*
-	 * Use CFS's precise accounting. (we subtract utime from
-	 * the total, to make sure the total observed by userspace
-	 * grows monotonically - apps rely on that):
-	 */
-	stime = nsec_to_clock_t(p->se.sum_exec_runtime) -
-			cputime_to_clock_t(task_utime(p));
-
-	if (stime >= 0)
-		p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime));
-
-	return p->prev_stime;
-}
-#endif
-
-static cputime_t task_gtime(struct task_struct *p)
-{
-	return p->gtime;
-}
-
 static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 			struct pid *pid, struct task_struct *task, int whole)
 {

@@ -1477,6 +1477,10 @@ static inline void put_task_struct(struc
 		__put_task_struct(t);
 }
 
+extern cputime_t task_utime(struct task_struct *p);
+extern cputime_t task_stime(struct task_struct *p);
+extern cputime_t task_gtime(struct task_struct *p);
+
 /*
  * Per process flags
  */

@@ -111,9 +111,9 @@ static void __exit_signal(struct task_st
 		 * We won't ever get here for the group leader, since it
 		 * will have been the last reference on the signal_struct.
 		 */
-		sig->utime = cputime_add(sig->utime, tsk->utime);
-		sig->stime = cputime_add(sig->stime, tsk->stime);
-		sig->gtime = cputime_add(sig->gtime, tsk->gtime);
+		sig->utime = cputime_add(sig->utime, task_utime(tsk));
+		sig->stime = cputime_add(sig->stime, task_stime(tsk));
+		sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
 		sig->min_flt += tsk->min_flt;
 		sig->maj_flt += tsk->maj_flt;
 		sig->nvcsw += tsk->nvcsw;

65 lines not on this page · raw message

@@ -1536,6 +1536,9 @@ void __cpuinit generic_processor_info(in
 		 */
 		cpu = 0;
 
+	if (apicid > max_physical_apicid)
+		max_physical_apicid = apicid;
+
 	/*
 	 * Would be preferable to switch to bigsmp when CONFIG_HOTPLUG_CPU=y
 	 * but we need to work other dependencies like SMP_SUSPEND etc

@@ -1543,7 +1546,7 @@ void __cpuinit generic_processor_info(in
 	 * if (CPU_HOTPLUG_ENABLED || num_processors > 8)
 	 *       - Ashok Raj <[email protected]>
 	 */
-	if (num_processors > 8) {
+	if (max_physical_apicid >= 8) {
 		switch (boot_cpu_data.x86_vendor) {
 		case X86_VENDOR_INTEL:
 			if (!APIC_XAPIC(version)) {

@@ -1090,6 +1090,9 @@ void __cpuinit generic_processor_info(in
 		 */
 		cpu = 0;
 	}
+	if (apicid > max_physical_apicid)
+		max_physical_apicid = apicid;
+
 	/* are we being called early in kernel startup? */
 	if (x86_cpu_to_apicid_early_ptr) {
 		u16 *cpu_to_apicid = x86_cpu_to_apicid_early_ptr;

@@ -51,7 +51,7 @@ void __init setup_apic_routing(void)
 	else
 #endif
 
-	if (num_possible_cpus() <= 8)
+	if (max_physical_apicid < 8)
 		genapic = &apic_flat;
 	else
 		genapic = &apic_physflat;

@@ -402,6 +402,11 @@ static int __init smp_read_mpc(struct mp
 		++mpc_record;
 #endif
 	}
+
+#ifdef CONFIG_X86_GENERICARCH
+       generic_bigsmp_probe();
+#endif
+
 	setup_apic_routing();
 	if (!num_processors)
 		printk(KERN_ERR "MPTABLE: no processors registered!\n");

@@ -914,6 +914,12 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_ACPI
 	acpi_boot_init();
+#endif
+
+#ifdef CONFIG_X86_LOCAL_APIC
+	if (smp_found_config)
+		get_smp_config();
+#endif
 
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_PC)
 	if (def_to_bigsmp)

@@ -921,11 +927,6 @@ void __init setup_arch(char **cmdline_p)
 			"CONFIG_X86_PC cannot handle it.\nUse "
 			"CONFIG_X86_GENERICARCH or CONFIG_X86_BIGSMP.\n");
 #endif
-#endif
-#ifdef CONFIG_X86_LOCAL_APIC
-	if (smp_found_config)
-		get_smp_config();
-#endif
 
 	e820_register_memory();
 	e820_mark_nosave_regions();

@@ -17,6 +17,7 @@ unsigned int num_processors;
 unsigned disabled_cpus __cpuinitdata;
 /* Processor that is doing the boot up */
 unsigned int boot_cpu_physical_apicid = -1U;
+unsigned int max_physical_apicid;
 EXPORT_SYMBOL(boot_cpu_physical_apicid);
 
 DEFINE_PER_CPU(u16, x86_cpu_to_apicid) = BAD_APICID;

@@ -48,7 +48,7 @@ static const struct dmi_system_id bigsmp
 static int probe_bigsmp(void)
 {
 	if (def_to_bigsmp)
-	dmi_bigsmp = 1;
+		dmi_bigsmp = 1;
 	else
 		dmi_check_system(bigsmp_dmi_table);
 	return dmi_bigsmp;

@@ -35,6 +35,7 @@ extern DECLARE_BITMAP(mp_bus_not_pci, MA
 extern int mp_bus_id_to_pci_bus[MAX_MP_BUSSES];
 
 extern unsigned int boot_cpu_physical_apicid;
+extern unsigned int max_physical_apicid;
 extern int smp_found_config;
 extern int mpc_default_type;
 extern unsigned long mp_lapic_addr;

@@ -97,13 +97,14 @@ static int ocfs2_stack_driver_request(co
 		goto out;
 	}
 
-	/* Ok, the stack is pinned */
-	p->sp_count++;
 	active_stack = p;
-
 	rc = 0;
 
 out:
+	/* If we found it, pin it */
+	if (!rc)
+		active_stack->sp_count++;
+
 	spin_unlock(&ocfs2_stack_lock);
 	return rc;
 }

@@ -312,8 +312,9 @@ static size_t sg_copy_buffer(struct scat
 	struct scatterlist *sg;
 	size_t buf_off = 0;
 	int i;
+	unsigned long flags;
 
-	WARN_ON(!irqs_disabled());
+	local_irq_save(flags);
 
 	for_each_sg(sgl, sg, nents, i) {
 		struct page *page;

@@ -358,6 +359,8 @@ static size_t sg_copy_buffer(struct scat
 			break;
 	}
 
+	local_irq_restore(flags);
+
 	return buf_off;
 }
 

@@ -58,7 +58,7 @@ static void vsmp_irq_enable(void)
 	native_restore_fl((flags | X86_EFLAGS_IF) & (~X86_EFLAGS_AC));
 }
 
-static unsigned __init vsmp_patch(u8 type, u16 clobbers, void *ibuf,
+static unsigned __init_or_module vsmp_patch(u8 type, u16 clobbers, void *ibuf,
 				  unsigned long addr, unsigned len)
 {
 	switch (type) {

@@ -75,7 +75,7 @@ static void rt2x00lib_start_link_tuner(s
 
 	rt2x00lib_reset_link_tuner(rt2x00dev);
 
-	queue_delayed_work(rt2x00dev->workqueue,
+	queue_delayed_work(rt2x00dev->hw->workqueue,
 			   &rt2x00dev->link.work, LINK_TUNE_INTERVAL);
 }
 

@@ -390,7 +390,7 @@ static void rt2x00lib_link_tuner(struct 
 	 * Increase tuner counter, and reschedule the next link tuner run.
 	 */
 	rt2x00dev->link.count++;
-	queue_delayed_work(rt2x00dev->workqueue,
+	queue_delayed_work(rt2x00dev->hw->workqueue,
 			   &rt2x00dev->link.work, LINK_TUNE_INTERVAL);
 }
 

@@ -488,7 +488,7 @@ void rt2x00lib_beacondone(struct rt2x00_
 						   rt2x00lib_beacondone_iter,
 						   rt2x00dev);
 
-	queue_work(rt2x00dev->workqueue, &rt2x00dev->intf_work);
+	schedule_work(&rt2x00dev->intf_work);
 }
 EXPORT_SYMBOL_GPL(rt2x00lib_beacondone);
 

@@ -1131,10 +1131,6 @@ int rt2x00lib_probe_dev(struct rt2x00_de
 	/*
 	 * Initialize configuration work.
 	 */
-	rt2x00dev->workqueue = create_singlethread_workqueue("rt2x00lib");
-	if (!rt2x00dev->workqueue)
-		goto exit;
-
 	INIT_WORK(&rt2x00dev->intf_work, rt2x00lib_intf_scheduled);
 	INIT_WORK(&rt2x00dev->filter_work, rt2x00lib_packetfilter_scheduled);
 	INIT_DELAYED_WORK(&rt2x00dev->link.work, rt2x00lib_link_tuner);

@@ -1195,13 +1191,6 @@ void rt2x00lib_remove_dev(struct rt2x00_
 	rt2x00leds_unregister(rt2x00dev);
 
 	/*
-	 * Stop all queued work. Note that most tasks will already be halted
-	 * during rt2x00lib_disable_radio() and rt2x00lib_uninitialize().
-	 */
-	flush_workqueue(rt2x00dev->workqueue);
-	destroy_workqueue(rt2x00dev->workqueue);
-
-	/*
 	 * Free ieee80211_hw memory.
 	 */
 	rt2x00lib_remove_hw(rt2x00dev);

@@ -820,8 +820,10 @@ struct rt2x00_dev {
 
 	/*
 	 * Scheduled work.
+	 * NOTE: intf_work will use ieee80211_iterate_active_interfaces()
+	 * which means it cannot be placed on the hw->workqueue
+	 * due to RTNL locking requirements.
 	 */
-	struct workqueue_struct *workqueue;
 	struct work_struct intf_work;
 	struct work_struct filter_work;
 

@@ -428,7 +428,7 @@ void rt2x00mac_configure_filter(struct i
 	if (!test_bit(DRIVER_REQUIRE_SCHEDULED, &rt2x00dev->flags))
 		rt2x00dev->ops->lib->config_filter(rt2x00dev, *total_flags);
 	else
-		queue_work(rt2x00dev->workqueue, &rt2x00dev->filter_work);
+		queue_work(rt2x00dev->hw->workqueue, &rt2x00dev->filter_work);
 }
 EXPORT_SYMBOL_GPL(rt2x00mac_configure_filter);
 

@@ -509,7 +509,7 @@ void rt2x00mac_bss_info_changed(struct i
 	memcpy(&intf->conf, bss_conf, sizeof(*bss_conf));
 	if (delayed) {
 		intf->delayed_flags |= delayed;
-		queue_work(rt2x00dev->workqueue, &rt2x00dev->intf_work);
+		schedule_work(&rt2x00dev->intf_work);
 	}
 	spin_unlock(&intf->lock);
 }

@@ -50,6 +50,8 @@ static double __initdata y = 3145727.0;
  */
 static void __init check_fpu(void)
 {
+	s32 fdiv_bug;
+
 	if (!boot_cpu_data.hard_math) {
 #ifndef CONFIG_MATH_EMULATION
 		printk(KERN_EMERG "No coprocessor found and no math emulation present.\n");

@@ -70,8 +72,10 @@ static void __init check_fpu(void)
 		"fistpl %0\n\t"
 		"fwait\n\t"
 		"fninit"
-		: "=m" (*&boot_cpu_data.fdiv_bug)
+		: "=m" (*&fdiv_bug)
 		: "m" (*&x), "m" (*&y));
+
+	boot_cpu_data.fdiv_bug = fdiv_bug;
 	if (boot_cpu_data.fdiv_bug)
 		printk("Hmm, FPU with FDIV bug.\n");
 }

@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/moduleparam.h>
 #include <linux/kdebug.h>
+#include <linux/cpu.h>
 #include <asm/nmi.h>
 #include <asm/msr.h>
 #include <asm/apic.h>

@@ -28,23 +29,48 @@ static DEFINE_PER_CPU(unsigned long, sav
 
 static int nmi_start(void);
 static void nmi_stop(void);
+static void nmi_cpu_start(void *dummy);
+static void nmi_cpu_stop(void *dummy);
 
 /* 0 == registered but off, 1 == registered and on */
 static int nmi_enabled = 0;
 
+#ifdef CONFIG_SMP
+static int oprofile_cpu_notifier(struct notifier_block *b, unsigned long action,
+				 void *data)
+{
+	int cpu = (unsigned long)data;
+	switch (action) {
+	case CPU_DOWN_FAILED:
+	case CPU_ONLINE:
+		smp_call_function_single(cpu, nmi_cpu_start, NULL, 0, 0);
+		break;
+	case CPU_DOWN_PREPARE:
+		smp_call_function_single(cpu, nmi_cpu_stop, NULL, 0, 1);
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block oprofile_cpu_nb = {
+	.notifier_call = oprofile_cpu_notifier
+};
+#endif
+
 #ifdef CONFIG_PM
 
 static int nmi_suspend(struct sys_device *dev, pm_message_t state)
 {
+	/* Only one CPU left, just stop that one */
 	if (nmi_enabled == 1)
-		nmi_stop();
+		nmi_cpu_stop(NULL);
 	return 0;
 }
 
 static int nmi_resume(struct sys_device *dev)
 {
 	if (nmi_enabled == 1)
-		nmi_start();
+		nmi_cpu_start(NULL);
 	return 0;
 }
 

@@ -448,6 +474,9 @@ int __init op_nmi_init(struct oprofile_o
 	}
 
 	init_sysfs();
+#ifdef CONFIG_SMP
+	register_cpu_notifier(&oprofile_cpu_nb);
+#endif
 	using_nmi = 1;
 	ops->create_files = nmi_create_files;
 	ops->setup = nmi_setup;

@@ -461,6 +490,10 @@ int __init op_nmi_init(struct oprofile_o
 
 void op_nmi_exit(void)
 {
-	if (using_nmi)
+	if (using_nmi) {
 		exit_sysfs();
+#ifdef CONFIG_SMP
+		unregister_cpu_notifier(&oprofile_cpu_nb);
+#endif
+	}
 }

@@ -789,7 +789,7 @@ int set_memory_uc(unsigned long addr, in
 	/*
 	 * for now UC MINUS. see comments in ioremap_nocache()
 	 */
-	if (reserve_memtype(addr, addr + numpages * PAGE_SIZE,
+	if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
 			    _PAGE_CACHE_UC_MINUS, NULL))
 		return -EINVAL;
 

@@ -808,7 +808,7 @@ int set_memory_wc(unsigned long addr, in
 	if (!pat_wc_enabled)
 		return set_memory_uc(addr, numpages);
 
-	if (reserve_memtype(addr, addr + numpages * PAGE_SIZE,
+	if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
 		_PAGE_CACHE_WC, NULL))
 		return -EINVAL;
 

@@ -824,7 +824,7 @@ int _set_memory_wb(unsigned long addr, i
 
 int set_memory_wb(unsigned long addr, int numpages)
 {
-	free_memtype(addr, addr + numpages * PAGE_SIZE);
+	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
 
 	return _set_memory_wb(addr, numpages);
 }

@@ -135,6 +135,7 @@ void __init x86_64_start_kernel(char * r
 	BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL));
 	BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) ==
 				(__START_KERNEL & PGDIR_MASK)));
+	BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END);
 
 	/* clear bss before set_intr_gate with early_idt_handler */
 	clear_bss();

@@ -146,7 +146,7 @@ static inline void native_pgd_clear(pgd_
 #define VMALLOC_END      _AC(0xffffe1ffffffffff, UL)
 #define VMEMMAP_START	 _AC(0xffffe20000000000, UL)
 #define MODULES_VADDR    _AC(0xffffffffa0000000, UL)
-#define MODULES_END      _AC(0xfffffffffff00000, UL)
+#define MODULES_END      _AC(0xffffffffff000000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
 
 #ifndef __ASSEMBLY__

@@ -94,7 +94,7 @@ int try_to_unmap(struct page *, int igno
  * Called from mm/filemap_xip.c to unmap empty zero page
  */
 pte_t *page_check_address(struct page *, struct mm_struct *,
-				unsigned long, spinlock_t **);
+				unsigned long, spinlock_t **, int);
 
 /*
  * Used by swapoff to help locate where page is expected in vma.

@@ -184,7 +184,7 @@ __xip_unmap (struct address_space * mapp
 		address = vma->vm_start +
 			((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
 		BUG_ON(address < vma->vm_start || address >= vma->vm_end);
-		pte = page_check_address(page, mm, address, &ptl);
+		pte = page_check_address(page, mm, address, &ptl, 1);
 		if (pte) {
 			/* Nuke the page table entry. */
 			flush_cache_page(vma, address, pte_pfn(*pte));

@@ -223,10 +223,14 @@ unsigned long page_address_in_vma(struct
 /*
  * Check that @page is mapped at @address into @mm.
  *
+ * If @sync is false, page_check_address may perform a racy check to avoid
+ * the page table lock when the pte is not present (helpful when reclaiming
+ * highly shared pages).
+ *
  * On success returns with pte mapped and locked.
  */
 pte_t *page_check_address(struct page *page, struct mm_struct *mm,
-			  unsigned long address, spinlock_t **ptlp)
+			  unsigned long address, spinlock_t **ptlp, int sync)
 {
 	pgd_t *pgd;
 	pud_t *pud;

@@ -248,7 +252,7 @@ pte_t *page_check_address(struct page *p
 
 	pte = pte_offset_map(pmd, address);
 	/* Make a quick check before getting the lock */
-	if (!pte_present(*pte)) {
+	if (!sync && !pte_present(*pte)) {
 		pte_unmap(pte);
 		return NULL;
 	}

@@ -280,7 +284,7 @@ static int page_referenced_one(struct pa
 	if (address == -EFAULT)
 		goto out;
 
-	pte = page_check_address(page, mm, address, &ptl);
+	pte = page_check_address(page, mm, address, &ptl, 0);
 	if (!pte)
 		goto out;
 

@@ -449,7 +453,7 @@ static int page_mkclean_one(struct page 
 	if (address == -EFAULT)
 		goto out;
 
-	pte = page_check_address(page, mm, address, &ptl);
+	pte = page_check_address(page, mm, address, &ptl, 1);
 	if (!pte)
 		goto out;
 

@@ -707,7 +711,7 @@ static int try_to_unmap_one(struct page 
 	if (address == -EFAULT)
 		goto out;
 
-	pte = page_check_address(page, mm, address, &ptl);
+	pte = page_check_address(page, mm, address, &ptl, 0);
 	if (!pte)
 		goto out;
 

@@ -15,6 +15,7 @@
 #include <linux/mc146818rtc.h>
 #include <linux/rtc.h>
 #include <linux/bcd.h>
+#include <linux/delay.h>
 
 #define RTC_PIE 0x40		/* periodic interrupt enable */
 #define RTC_AIE 0x20		/* alarm interrupt enable */

@@ -43,7 +44,6 @@ static inline unsigned char rtc_is_updat
 
 static inline unsigned int get_rtc_time(struct rtc_time *time)
 {
-	unsigned long uip_watchdog = jiffies;
 	unsigned char ctrl;
 	unsigned long flags;
 

@@ -53,19 +53,15 @@ static inline unsigned int get_rtc_time(
 
 	/*
 	 * read RTC once any update in progress is done. The update
-	 * can take just over 2ms. We wait 10 to 20ms. There is no need to
+	 * can take just over 2ms. We wait 20ms. There is no need to
 	 * to poll-wait (up to 1s - eeccch) for the falling edge of RTC_UIP.
 	 * If you need to know *exactly* when a second has started, enable
 	 * periodic update complete interrupts, (via ioctl) and then 
 	 * immediately read /dev/rtc which will block until you get the IRQ.
 	 * Once the read clears, read the RTC time (again via ioctl). Easy.
 	 */
-
-	if (rtc_is_updating() != 0)
-		while (jiffies - uip_watchdog < 2*HZ/100) {
-			barrier();
-			cpu_relax();
-		}
+	if (rtc_is_updating())
+		mdelay(20);
 
 	/*
 	 * Only the values that we read from the RTC are set. We leave

@@ -196,6 +196,8 @@ static int acpi_ec_wait(struct acpi_ec *
 				return 0;
 			msleep(1);
 		}
+		if (acpi_ec_check_status(ec,event))
+			return 0;
 	}
 	pr_err(PREFIX "acpi_ec_wait timeout, status = 0x%2.2x, event = %s\n",
 		acpi_ec_read_status(ec),

@@ -92,6 +92,14 @@ static struct dmi_system_id __initdata i
 			DMI_MATCH(DMI_BOARD_NAME, "30BF")
 		}
 	},
+	{
+		.callback	= dmi_io_delay_0xed_port,
+		.ident		= "Presario F700",
+		.matches	= {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Quanta"),
+			DMI_MATCH(DMI_BOARD_NAME, "30D3")
+		}
+	},
 	{ }
 };
 

@@ -697,7 +697,7 @@ static int __init parse_memmap(char *arg
 	if (!arg)
 		return -EINVAL;
 
-	if (strcmp(arg, "exactmap") == 0) {
+	if (strncmp(arg, "exactmap", 8) == 0) {
 #ifdef CONFIG_CRASH_DUMP
 		/* If we are doing a crash dump, we
 		 * still need to know the real mem

@@ -776,7 +776,7 @@ static int __init parse_memmap_opt(char 
 	char *oldp;
 	unsigned long long start_at, mem_size;
 
-	if (!strcmp(p, "exactmap")) {
+	if (!strncmp(p, "exactmap", 8)) {
 #ifdef CONFIG_CRASH_DUMP
 		/*
 		 * If we are doing a crash dump, we still need to know

@@ -127,6 +127,8 @@ extern int clockevents_register_notifier
 extern int clockevents_program_event(struct clock_event_device *dev,
 				     ktime_t expires, ktime_t now);
 
+extern void clockevents_handle_noop(struct clock_event_device *dev);
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 extern void clockevents_notify(unsigned long reason, void *arg);
 #else

@@ -177,7 +177,7 @@ void clockevents_register_device(struct 
 /*
  * Noop handler when we shut down an event device
  */
-static void clockevents_handle_noop(struct clock_event_device *dev)
+void clockevents_handle_noop(struct clock_event_device *dev)
 {
 }
 

@@ -199,7 +199,6 @@ void clockevents_exchange_device(struct 
 	 * released list and do a notify add later.
 	 */
 	if (old) {
-		old->event_handler = clockevents_handle_noop;
 		clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
 		list_del(&old->list);
 		list_add(&old->list, &clockevents_released);

@@ -161,6 +161,7 @@ static void tick_setup_device(struct tic
 	} else {
 		handler = td->evtdev->event_handler;
 		next_event = td->evtdev->next_event;
+		td->evtdev->event_handler = clockevents_handle_noop;
 	}
 
 	td->evtdev = newdev;

@@ -174,6 +174,8 @@ static void tick_do_periodic_broadcast(v
  */
 static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
 {
+	ktime_t next;
+
 	tick_do_periodic_broadcast();
 
 	/*

@@ -184,10 +186,13 @@ static void tick_handle_periodic_broadca
 
 	/*
 	 * Setup the next period for devices, which do not have
-	 * periodic mode:
+	 * periodic mode. We read dev->next_event first and add to it
+	 * when the event alrady expired. clockevents_program_event()
+	 * sets dev->next_event only when the event is really
+	 * programmed to the device.
 	 */
-	for (;;) {
-		ktime_t next = ktime_add(dev->next_event, tick_period);
+	for (next = dev->next_event; ;) {
+		next = ktime_add(next, tick_period);
 
 		if (!clockevents_program_event(dev, next, ktime_get()))
 			return;

@@ -23,11 +23,11 @@
 #include "tick-internal.h"
 
 /**
- * tick_program_event
+ * tick_program_event internal worker function
  */
-int tick_program_event(ktime_t expires, int force)
+static int __tick_program_event(struct clock_event_device *dev,
+				ktime_t expires, int force)
 {
-	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
 	ktime_t now = ktime_get();
 
 	while (1) {

@@ -41,6 +41,16 @@ int tick_program_event(ktime_t expires, 
 }
 
 /**
+ * tick_program_event
+ */
+int tick_program_event(ktime_t expires, int force)
+{
+	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
+
+	return __tick_program_event(dev, expires, force);
+}
+
+/**
  * tick_resume_onshot - resume oneshot mode
  */
 void tick_resume_oneshot(void)

@@ -61,7 +71,7 @@ void tick_setup_oneshot(struct clock_eve
 {
 	newdev->event_handler = handler;
 	clockevents_set_mode(newdev, CLOCK_EVT_MODE_ONESHOT);
-	clockevents_program_event(newdev, next_event, ktime_get());
+	__tick_program_event(newdev, next_event, 1);
 }
 
 /**

@@ -209,7 +209,7 @@ static void tick_do_broadcast_on_off(voi
 	struct clock_event_device *bc, *dev;
 	struct tick_device *td;
 	unsigned long flags, *reason = why;
-	int cpu;
+	int cpu, bc_stopped;
 
 	spin_lock_irqsave(&tick_broadcast_lock, flags);
 

@@ -227,6 +227,8 @@ static void tick_do_broadcast_on_off(voi
 	if (!tick_device_is_functional(dev))
 		goto out;
 
+	bc_stopped = cpus_empty(tick_broadcast_mask);
+
 	switch (*reason) {
 	case CLOCK_EVT_NOTIFY_BROADCAST_ON:
 	case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:

@@ -248,9 +250,10 @@ static void tick_do_broadcast_on_off(voi
 		break;
 	}
 
-	if (cpus_empty(tick_broadcast_mask))
-		clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
-	else {
+	if (cpus_empty(tick_broadcast_mask)) {
+		if (!bc_stopped)
+			clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
+	} else if (bc_stopped) {
 		if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
 			tick_broadcast_start_periodic(bc);
 		else

@@ -500,9 +503,12 @@ static void tick_broadcast_clear_oneshot
  */
 void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 {
-	bc->event_handler = tick_handle_oneshot_broadcast;
-	clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
-	bc->next_event.tv64 = KTIME_MAX;
+	/* Set it up only once ! */
+	if (bc->event_handler != tick_handle_oneshot_broadcast) {
+		bc->event_handler = tick_handle_oneshot_broadcast;
+		clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
+		bc->next_event.tv64 = KTIME_MAX;
+	}
 }
 
 /*

@@ -370,16 +370,8 @@ cpumask_t *tick_get_broadcast_oneshot_ma
 static int tick_broadcast_set_event(ktime_t expires, int force)
 {
 	struct clock_event_device *bc = tick_broadcast_device.evtdev;
-	ktime_t now = ktime_get();
-	int res;
 
-	for(;;) {
-		res = clockevents_program_event(bc, expires, now);
-		if (!res || !force)
-			return res;
-		now = ktime_get();
-		expires = ktime_add(now, ktime_set(0, bc->min_delta_ns));
-	}
+	return tick_dev_program_event(bc, expires, force);
 }
 
 int tick_resume_broadcast_oneshot(struct clock_event_device *bc)

@@ -17,6 +17,8 @@ extern void tick_handle_periodic(struct 
 extern void tick_setup_oneshot(struct clock_event_device *newdev,
 			       void (*handler)(struct clock_event_device *),
 			       ktime_t nextevt);
+extern int tick_dev_program_event(struct clock_event_device *dev,
+				  ktime_t expires, int force);
 extern int tick_program_event(ktime_t expires, int force);
 extern void tick_oneshot_notify(void);
 extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *));

@@ -25,18 +25,42 @@
 /**
  * tick_program_event internal worker function
  */
-static int __tick_program_event(struct clock_event_device *dev,
-				ktime_t expires, int force)
+int tick_dev_program_event(struct clock_event_device *dev, ktime_t expires,
+			   int force)
 {
 	ktime_t now = ktime_get();
+	int i;
 
-	while (1) {
+	for (i = 0;;) {
 		int ret = clockevents_program_event(dev, expires, now);
 
 		if (!ret || !force)
 			return ret;
+
+		/*
+		 * We tried 2 times to program the device with the given
+		 * min_delta_ns. If that's not working then we double it
+		 * and emit a warning.
+		 */
+		if (++i > 2) {
+			printk(KERN_WARNING "CE: __tick_program_event of %s is "
+			       "stuck %llx %llx\n", dev->name ? dev->name : "?",
+			       now.tv64, expires.tv64);
+			printk(KERN_WARNING
+			       "CE: increasing min_delta_ns %ld to %ld nsec\n",
+			       dev->min_delta_ns, dev->min_delta_ns << 1);
+			WARN_ON(1);
+
+			/* Double the min. delta and try again */
+			if (!dev->min_delta_ns)
+				dev->min_delta_ns = 5000;
+			else
+				dev->min_delta_ns <<= 1;
+			i = 0;
+		}
+
 		now = ktime_get();
-		expires = ktime_add(now, ktime_set(0, dev->min_delta_ns));
+		expires = ktime_add_ns(now, dev->min_delta_ns);
 	}
 }
 

@@ -47,7 +71,7 @@ int tick_program_event(ktime_t expires, 
 {
 	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
 
-	return __tick_program_event(dev, expires, force);
+	return tick_dev_program_event(dev, expires, force);
 }
 
 /**

@@ -71,7 +95,7 @@ void tick_setup_oneshot(struct clock_eve
 {
 	newdev->event_handler = handler;
 	clockevents_set_mode(newdev, CLOCK_EVT_MODE_ONESHOT);
-	__tick_program_event(newdev, next_event, 1);
+	tick_dev_program_event(newdev, next_event, 1);
 }
 
 /**

@@ -223,8 +223,8 @@ static void hpet_legacy_clockevent_regis
 	/* Calculate the min / max delta */
 	hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
 							   &hpet_clockevent);
-	hpet_clockevent.min_delta_ns = clockevent_delta2ns(0x30,
-							   &hpet_clockevent);
+	/* 5 usec minimum reprogramming delta. */
+	hpet_clockevent.min_delta_ns = 5000;
 
 	/*
 	 * Start hpet with the boot cpu mask and make it

@@ -490,6 +490,18 @@ static void tick_broadcast_clear_oneshot
 	cpu_clear(cpu, tick_broadcast_oneshot_mask);
 }
 
+static void tick_broadcast_init_next_event(cpumask_t *mask, ktime_t expires)
+{
+	struct tick_device *td;
+	int cpu;
+
+	for_each_cpu_mask_nr(cpu, *mask) {
+		td = &per_cpu(tick_cpu_device, cpu);
+		if (td->evtdev)
+			td->evtdev->next_event = expires;
+	}
+}
+
 /**
  * tick_broadcast_setup_oneshot - setup the broadcast device
  */

@@ -497,9 +509,32 @@ void tick_broadcast_setup_oneshot(struct
 {
 	/* Set it up only once ! */
 	if (bc->event_handler != tick_handle_oneshot_broadcast) {
+		int was_periodic = bc->mode == CLOCK_EVT_MODE_PERIODIC;
+		int cpu = smp_processor_id();
+		cpumask_t mask;
+
 		bc->event_handler = tick_handle_oneshot_broadcast;
 		clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
-		bc->next_event.tv64 = KTIME_MAX;
+
+		/* Take the do_timer update */
+		tick_do_timer_cpu = cpu;
+
+		/*
+		 * We must be careful here. There might be other CPUs
+		 * waiting for periodic broadcast. We need to set the
+		 * oneshot_mask bits for those and program the
+		 * broadcast device to fire.
+		 */
+		mask = tick_broadcast_mask;
+		cpu_clear(cpu, mask);
+		cpus_or(tick_broadcast_oneshot_mask,
+			tick_broadcast_oneshot_mask, mask);
+
+		if (was_periodic && !cpus_empty(mask)) {
+			tick_broadcast_init_next_event(&mask, tick_next_period);
+			tick_broadcast_set_event(tick_next_period, 1);
+		} else
+			bc->next_event.tv64 = KTIME_MAX;
 	}
 }
 

@@ -283,15 +283,15 @@ static void hpet_legacy_set_mode(enum cl
 }
 
 static int hpet_legacy_next_event(unsigned long delta,
-			   struct clock_event_device *evt)
+				  struct clock_event_device *evt)
 {
-	unsigned long cnt;
+	u32 cnt;
 
 	cnt = hpet_readl(HPET_COUNTER);
-	cnt += delta;
+	cnt += (u32) delta;
 	hpet_writel(cnt, HPET_T0_CMP);
 
-	return ((long)(hpet_readl(HPET_COUNTER) - cnt ) > 0) ? -ETIME : 0;
+	return (s32)((u32)hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0;
 }
 
 /*

@@ -291,6 +291,13 @@ static int hpet_legacy_next_event(unsign
 	cnt += (u32) delta;
 	hpet_writel(cnt, HPET_T0_CMP);
 
+	/*
+	 * We need to read back the CMP register to make sure that
+	 * what we wrote hit the chip before we compare it to the
+	 * counter.
+	 */
+	WARN_ON((u32)hpet_readl(HPET_T0_CMP) != cnt);
+
 	return (s32)((u32)hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0;
 }
 

@@ -245,7 +245,7 @@ static void sync_cmos_clock(unsigned lon
 	if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2)
 		fail = update_persistent_clock(now);
 
-	next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec;
+	next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec - (TICK_NSEC / 2);
 	if (next.tv_nsec <= 0)
 		next.tv_nsec += NSEC_PER_SEC;
 

@@ -43,19 +43,17 @@ int tick_dev_program_event(struct clock_
 		 * and emit a warning.
 		 */
 		if (++i > 2) {
-			printk(KERN_WARNING "CE: __tick_program_event of %s is "
-			       "stuck %llx %llx\n", dev->name ? dev->name : "?",
-			       now.tv64, expires.tv64);
-			printk(KERN_WARNING
-			       "CE: increasing min_delta_ns %ld to %ld nsec\n",
-			       dev->min_delta_ns, dev->min_delta_ns << 1);
-			WARN_ON(1);
-
-			/* Double the min. delta and try again */
+			/* Increase the min. delta and try again */
 			if (!dev->min_delta_ns)
 				dev->min_delta_ns = 5000;
 			else
-				dev->min_delta_ns <<= 1;
+				dev->min_delta_ns += dev->min_delta_ns >> 1;
+
+			printk(KERN_WARNING
+			       "CE: %s increasing min_delta_ns to %lu nsec\n",
+			       dev->name ? dev->name : "?",
+			       dev->min_delta_ns << 1);
+
 			i = 0;
 		}
 

@@ -428,6 +428,18 @@ static int pcmcia_device_probe(struct de
 	p_drv = to_pcmcia_drv(dev->driver);
 	s = p_dev->socket;
 
+	/* The PCMCIA code passes the match data in via dev->driver_data
+	 * which is an ugly hack. Once the driver probe is called it may
+	 * and often will overwrite the match data so we must save it first
+	 *
+	 * handle pseudo multifunction devices:
+	 * there are at most two pseudo multifunction devices.
+	 * if we're matching against the first, schedule a
+	 * call which will then check whether there are two
+	 * pseudo devices, and if not, add the second one.
+	 */
+	did = p_dev->dev.driver_data;
+
 	ds_dbg(1, "trying to bind %s to %s\n", p_dev->dev.bus_id,
 	       p_drv->drv.name);
 

@@ -456,21 +468,14 @@ static int pcmcia_device_probe(struct de
 		goto put_module;
 	}
 
-	/* handle pseudo multifunction devices:
-	 * there are at most two pseudo multifunction devices.
-	 * if we're matching against the first, schedule a
-	 * call which will then check whether there are two
-	 * pseudo devices, and if not, add the second one.
-	 */
-	did = p_dev->dev.driver_data;
 	if (did && (did->match_flags & PCMCIA_DEV_ID_MATCH_DEVICE_NO) &&
 	    (p_dev->socket->device_count == 1) && (p_dev->device_no == 0))
 		pcmcia_add_device_later(p_dev->socket, 0);
 
- put_module:
+put_module:
 	if (ret)
 		module_put(p_drv->owner);
- put_dev:
+put_dev:
 	if (ret)
 		put_device(dev);
 	return (ret);

@@ -73,22 +73,18 @@ static int pfkey_can_dump(struct sock *s
 	return 0;
 }
 
-static int pfkey_do_dump(struct pfkey_sock *pfk)
+static void pfkey_terminate_dump(struct pfkey_sock *pfk)
 {
-	int rc;
-
-	rc = pfk->dump.dump(pfk);
-	if (rc == -ENOBUFS)
-		return 0;
-
-	pfk->dump.done(pfk);
-	pfk->dump.dump = NULL;
-	pfk->dump.done = NULL;
-	return rc;
+	if (pfk->dump.dump) {
+		pfk->dump.done(pfk);
+		pfk->dump.dump = NULL;
+		pfk->dump.done = NULL;
+	}
 }
 
 static void pfkey_sock_destruct(struct sock *sk)
 {
+	pfkey_terminate_dump(pfkey_sk(sk));
 	skb_queue_purge(&sk->sk_receive_queue);
 
 	if (!sock_flag(sk, SOCK_DEAD)) {

@@ -310,6 +306,18 @@ static int pfkey_broadcast(struct sk_buf
 	return err;
 }
 
+static int pfkey_do_dump(struct pfkey_sock *pfk)
+{
+	int rc;
+
+	rc = pfk->dump.dump(pfk);
+	if (rc == -ENOBUFS)
+		return 0;
+
+	pfkey_terminate_dump(pfk);
+	return rc;
+}
+
 static inline void pfkey_hdr_dup(struct sadb_msg *new, struct sadb_msg *orig)
 {
 	*new = *orig;

@@ -2718,6 +2718,8 @@ int __init ip6_route_init(void)
 	if (ret)
 		goto out_kmem_cache;
 
+	ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep;
+
 	/* Registering of the loopback is done before this portion of code,
 	 * the loopback reference in rt6_info will not be taken, do it
 	 * manually for init_net */

@@ -934,39 +934,39 @@ static int ip6_dst_lookup_tail(struct so
 	}
 
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
-		/*
-		 * Here if the dst entry we've looked up
-		 * has a neighbour entry that is in the INCOMPLETE
-		 * state and the src address from the flow is
-		 * marked as OPTIMISTIC, we release the found
-		 * dst entry and replace it instead with the
-		 * dst entry of the nexthop router
-		 */
-		if (!((*dst)->neighbour->nud_state & NUD_VALID)) {
-			struct inet6_ifaddr *ifp;
-			struct flowi fl_gw;
-			int redirect;
-
-			ifp = ipv6_get_ifaddr(net, &fl->fl6_src,
-					      (*dst)->dev, 1);
-
-			redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC);
-			if (ifp)
-				in6_ifa_put(ifp);
-
-			if (redirect) {
-				/*
-				 * We need to get the dst entry for the
-				 * default router instead
-				 */
-				dst_release(*dst);
-				memcpy(&fl_gw, fl, sizeof(struct flowi));
-				memset(&fl_gw.fl6_dst, 0, sizeof(struct in6_addr));
-				*dst = ip6_route_output(net, sk, &fl_gw);
-				if ((err = (*dst)->error))
-					goto out_err_release;
-			}
+	/*
+	 * Here if the dst entry we've looked up
+	 * has a neighbour entry that is in the INCOMPLETE
+	 * state and the src address from the flow is
+	 * marked as OPTIMISTIC, we release the found
+	 * dst entry and replace it instead with the
+	 * dst entry of the nexthop router
+	 */
+	if ((*dst)->neighbour && !((*dst)->neighbour->nud_state & NUD_VALID)) {
+		struct inet6_ifaddr *ifp;
+		struct flowi fl_gw;
+		int redirect;
+
+		ifp = ipv6_get_ifaddr(net, &fl->fl6_src,
+				      (*dst)->dev, 1);
+
+		redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC);
+		if (ifp)
+			in6_ifa_put(ifp);
+
+		if (redirect) {
+			/*
+			 * We need to get the dst entry for the
+			 * default router instead
+			 */
+			dst_release(*dst);
+			memcpy(&fl_gw, fl, sizeof(struct flowi));
+			memset(&fl_gw.fl6_dst, 0, sizeof(struct in6_addr));
+			*dst = ip6_route_output(net, sk, &fl_gw);
+			if ((err = (*dst)->error))
+				goto out_err_release;
 		}
+	}
 #endif
 
 	return 0;

@@ -5978,6 +5978,56 @@ static void niu_netif_start(struct niu *
 	niu_enable_interrupts(np, 1);
 }
 
+static void niu_reset_buffers(struct niu *np)
+{
+	int i, j, k, err;
+
+	if (np->rx_rings) {
+		for (i = 0; i < np->num_rx_rings; i++) {
+			struct rx_ring_info *rp = &np->rx_rings[i];
+
+			for (j = 0, k = 0; j < MAX_RBR_RING_SIZE; j++) {
+				struct page *page;
+
+				page = rp->rxhash[j];
+				while (page) {
+					struct page *next =
+						(struct page *) page->mapping;
+					u64 base = page->index;
+					base = base >> RBR_DESCR_ADDR_SHIFT;
+					rp->rbr[k++] = cpu_to_le32(base);
+					page = next;
+				}
+			}
+			for (; k < MAX_RBR_RING_SIZE; k++) {
+				err = niu_rbr_add_page(np, rp, GFP_ATOMIC, k);
+				if (unlikely(err))
+					break;
+			}
+
+			rp->rbr_index = rp->rbr_table_size - 1;
+			rp->rcr_index = 0;
+			rp->rbr_pending = 0;
+			rp->rbr_refill_pending = 0;
+		}
+	}
+	if (np->tx_rings) {
+		for (i = 0; i < np->num_tx_rings; i++) {
+			struct tx_ring_info *rp = &np->tx_rings[i];
+
+			for (j = 0; j < MAX_TX_RING_SIZE; j++) {
+				if (rp->tx_buffs[j].skb)
+					(void) release_tx_packet(np, rp, j);
+			}
+
+			rp->pending = MAX_TX_RING_SIZE;
+			rp->prod = 0;
+			rp->cons = 0;
+			rp->wrap_bit = 0;
+		}
+	}
+}
+
 static void niu_reset_task(struct work_struct *work)
 {
 	struct niu *np = container_of(work, struct niu, reset_task);

@@ -6000,6 +6050,12 @@ static void niu_reset_task(struct work_s
 
 	niu_stop_hw(np);
 
+	spin_unlock_irqrestore(&np->lock, flags);
+
+	niu_reset_buffers(np);
+
+	spin_lock_irqsave(&np->lock, flags);
+
 	err = niu_init_hw(np);
 	if (!err) {
 		np->timer.expires = jiffies + HZ;

@@ -702,7 +702,7 @@ static inline int nla_len(const struct n
  */
 static inline int nla_ok(const struct nlattr *nla, int remaining)
 {
-	return remaining >= sizeof(*nla) &&
+	return remaining >= (int) sizeof(*nla) &&
 	       nla->nla_len >= sizeof(*nla) &&
 	       nla->nla_len <= remaining;
 }

@@ -27,10 +27,14 @@ static int xfrm_state_check_space(struct
 		- skb_headroom(skb);
 	int ntail = dst->dev->needed_tailroom - skb_tailroom(skb);
 
-	if (nhead > 0 || ntail > 0)
-		return pskb_expand_head(skb, nhead, ntail, GFP_ATOMIC);
+	if (nhead <= 0) {
+		if (ntail <= 0)
+			return 0;
+		nhead = 0;
+	} else if (ntail < 0)
+		ntail = 0;
 
-	return 0;
+	return pskb_expand_head(skb, nhead, ntail, GFP_ATOMIC);
 }
 
 static int xfrm_output_one(struct sk_buff *skb, int err)

@@ -1886,11 +1886,13 @@ static void sctp_process_ext_param(struc
 			    /* if the peer reports AUTH, assume that he
 			     * supports AUTH.
 			     */
-			    asoc->peer.auth_capable = 1;
+			    if (sctp_auth_enable)
+				    asoc->peer.auth_capable = 1;
 			    break;
 		    case SCTP_CID_ASCONF:
 		    case SCTP_CID_ASCONF_ACK:
-			    asoc->peer.asconf_capable = 1;
+			    if (sctp_addip_enable)
+				    asoc->peer.asconf_capable = 1;
 			    break;
 		    default:
 			    break;

@@ -2455,6 +2457,9 @@ static int sctp_process_param(struct sct
 		break;
 
 	case SCTP_PARAM_SET_PRIMARY:
+		if (!sctp_addip_enable)
+			goto fall_through;
+
 		addr_param = param.v + sizeof(sctp_addip_param_t);
 
 		af = sctp_get_af_specific(param_type2af(param.p->type));

@@ -597,11 +597,12 @@ struct sctp_transport *sctp_assoc_add_pe
 	/* Check to see if this is a duplicate. */
 	peer = sctp_assoc_lookup_paddr(asoc, addr);
 	if (peer) {
+		/* An UNKNOWN state is only set on transports added by
+		 * user in sctp_connectx() call.  Such transports should be
+		 * considered CONFIRMED per RFC 4960, Section 5.4.
+		 */
 		if (peer->state == SCTP_UNKNOWN) {
-			if (peer_state == SCTP_ACTIVE)
-				peer->state = SCTP_ACTIVE;
-			if (peer_state == SCTP_UNCONFIRMED)
-				peer->state = SCTP_UNCONFIRMED;
+			peer->state = SCTP_ACTIVE;
 		}
 		return peer;
 	}