Re: Linux 4.14.214

[Greg Kroah-Hartman]

diff --git a/Makefile b/Makefile
index d059e257b976..d36b8f4228a4 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 4
 PATCHLEVEL = 14
-SUBLEVEL = 213
+SUBLEVEL = 214
 EXTRAVERSION =
 NAME = Petit Gorille
 
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index b750ffef83c7..0ec93d940d12 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -220,15 +220,34 @@ static __inline__ void __clear_bit_unlock(int nr, volatile unsigned long *addr)
  */
 static __inline__ int fls(unsigned int x)
 {
-	return 32 - __builtin_clz(x);
+	int lz;
+
+	if (__builtin_constant_p(x))
+		return x ? 32 - __builtin_clz(x) : 0;
+	asm("cntlzw %0,%1" : "=r" (lz) : "r" (x));
+	return 32 - lz;
 }
 
 #include <asm-generic/bitops/builtin-__fls.h>
 
+/*
+ * 64-bit can do this using one cntlzd (count leading zeroes doubleword)
+ * instruction; for 32-bit we use the generic version, which does two
+ * 32-bit fls calls.
+ */
+#ifdef CONFIG_PPC64
 static __inline__ int fls64(__u64 x)
 {
-	return 64 - __builtin_clzll(x);
+	int lz;
+
+	if (__builtin_constant_p(x))
+		return x ? 64 - __builtin_clzll(x) : 0;
+	asm("cntlzd %0,%1" : "=r" (lz) : "r" (x));
+	return 64 - lz;
 }
+#else
+#include <asm-generic/bitops/fls64.h>
+#endif
 
 #ifdef CONFIG_PPC64
 unsigned int __arch_hweight8(unsigned int w);
diff --git a/arch/powerpc/sysdev/mpic_msgr.c b/arch/powerpc/sysdev/mpic_msgr.c
index 280e964e1aa8..497e86cfb12e 100644
--- a/arch/powerpc/sysdev/mpic_msgr.c
+++ b/arch/powerpc/sysdev/mpic_msgr.c
@@ -196,7 +196,7 @@ static int mpic_msgr_probe(struct platform_device *dev)
 
 	/* IO map the message register block. */
 	of_address_to_resource(np, 0, &rsrc);
-	msgr_block_addr = ioremap(rsrc.start, resource_size(&rsrc));
+	msgr_block_addr = devm_ioremap(&dev->dev, rsrc.start, resource_size(&rsrc));
 	if (!msgr_block_addr) {
 		dev_err(&dev->dev, "Failed to iomap MPIC message registers");
 		return -EFAULT;
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f24974bddfc9..ac389ffb1822 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -55,7 +55,7 @@ END(native_usergs_sysret64)
 
 .macro TRACE_IRQS_IRETQ
 #ifdef CONFIG_TRACE_IRQFLAGS
-	bt	$9, EFLAGS(%rsp)		/* interrupts off? */
+	btl	$9, EFLAGS(%rsp)		/* interrupts off? */
 	jnc	1f
 	TRACE_IRQS_ON
 1:
diff --git a/drivers/iio/imu/bmi160/bmi160_core.c b/drivers/iio/imu/bmi160/bmi160_core.c
index 01fcd715485c..c56512297fb9 100644
--- a/drivers/iio/imu/bmi160/bmi160_core.c
+++ b/drivers/iio/imu/bmi160/bmi160_core.c
@@ -110,6 +110,13 @@ enum bmi160_sensor_type {
 
 struct bmi160_data {
 	struct regmap *regmap;
+	/*
+	 * Ensure natural alignment for timestamp if present.
+	 * Max length needed: 2 * 3 channels + 4 bytes padding + 8 byte ts.
+	 * If fewer channels are enabled, less space may be needed, as
+	 * long as the timestamp is still aligned to 8 bytes.
+	 */
+	__le16 buf[12] __aligned(8);
 };
 
 const struct regmap_config bmi160_regmap_config = {
@@ -385,8 +392,6 @@ static irqreturn_t bmi160_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct bmi160_data *data = iio_priv(indio_dev);
-	__le16 buf[12];
-	/* 2 sens x 3 axis x __le16 + 2 x __le16 pad + 4 x __le16 tstamp */
 	int i, ret, j = 0, base = BMI160_REG_DATA_MAGN_XOUT_L;
 	__le16 sample;
 
@@ -396,10 +401,10 @@ static irqreturn_t bmi160_trigger_handler(int irq, void *p)
 				       &sample, sizeof(sample));
 		if (ret < 0)
 			goto done;
-		buf[j++] = sample;
+		data->buf[j++] = sample;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buf,
+	iio_push_to_buffers_with_timestamp(indio_dev, data->buf,
 					   iio_get_time_ns(indio_dev));
 done:
 	iio_trigger_notify_done(indio_dev->trig);
diff --git a/drivers/iio/magnetometer/mag3110.c b/drivers/iio/magnetometer/mag3110.c
index dad8d57f7402..974e141c0dc0 100644
--- a/drivers/iio/magnetometer/mag3110.c
+++ b/drivers/iio/magnetometer/mag3110.c
@@ -52,6 +52,12 @@ struct mag3110_data {
 	struct i2c_client *client;
 	struct mutex lock;
 	u8 ctrl_reg1;
+	/* Ensure natural alignment of timestamp */
+	struct {
+		__be16 channels[3];
+		u8 temperature;
+		s64 ts __aligned(8);
+	} scan;
 };
 
 static int mag3110_request(struct mag3110_data *data)
@@ -262,10 +268,9 @@ static irqreturn_t mag3110_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct mag3110_data *data = iio_priv(indio_dev);
-	u8 buffer[16]; /* 3 16-bit channels + 1 byte temp + padding + ts */
 	int ret;
 
-	ret = mag3110_read(data, (__be16 *) buffer);
+	ret = mag3110_read(data, data->scan.channels);
 	if (ret < 0)
 		goto done;
 
@@ -274,10 +279,10 @@ static irqreturn_t mag3110_trigger_handler(int irq, void *p)
 			MAG3110_DIE_TEMP);
 		if (ret < 0)
 			goto done;
-		buffer[6] = ret;
+		data->scan.temperature = ret;
 	}
 
-	iio_push_to_buffers_with_timestamp(indio_dev, buffer,
+	iio_push_to_buffers_with_timestamp(indio_dev, &data->scan,
 		iio_get_time_ns(indio_dev));
 
 done:
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index e705799976c2..2dae30713eb3 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -551,6 +551,15 @@ static int verity_verify_io(struct dm_verity_io *io)
 	return 0;
 }
 
+/*
+ * Skip verity work in response to I/O error when system is shutting down.
+ */
+static inline bool verity_is_system_shutting_down(void)
+{
+	return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF
+		|| system_state == SYSTEM_RESTART;
+}
+
 /*
  * End one "io" structure with a given error.
  */
@@ -578,7 +587,8 @@ static void verity_end_io(struct bio *bio)
 {
 	struct dm_verity_io *io = bio->bi_private;
 
-	if (bio->bi_status && !verity_fec_is_enabled(io->v)) {
+	if (bio->bi_status &&
+	    (!verity_fec_is_enabled(io->v) || verity_is_system_shutting_down())) {
 		verity_finish_io(io, bio->bi_status);
 		return;
 	}
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index d08d77b9674f..419ecdd914f4 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1120,7 +1120,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	struct md_rdev *err_rdev = NULL;
 	gfp_t gfp = GFP_NOIO;
 
-	if (r10_bio->devs[slot].rdev) {
+	if (slot >= 0 && r10_bio->devs[slot].rdev) {
 		/*
 		 * This is an error retry, but we cannot
 		 * safely dereference the rdev in the r10_bio,
@@ -1513,6 +1513,7 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
 	r10_bio->mddev = mddev;
 	r10_bio->sector = bio->bi_iter.bi_sector;
 	r10_bio->state = 0;
+	r10_bio->read_slot = -1;
 	memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * conf->copies);
 
 	if (bio_data_dir(bio) == READ)
diff --git a/drivers/media/usb/dvb-usb/gp8psk.c b/drivers/media/usb/dvb-usb/gp8psk.c
index 37f062225ed2..aac677f6aaa4 100644
--- a/drivers/media/usb/dvb-usb/gp8psk.c
+++ b/drivers/media/usb/dvb-usb/gp8psk.c
@@ -185,7 +185,7 @@ static int gp8psk_load_bcm4500fw(struct dvb_usb_device *d)
 
 static int gp8psk_power_ctrl(struct dvb_usb_device *d, int onoff)
 {
-	u8 status, buf;
+	u8 status = 0, buf;
 	int gp_product_id = le16_to_cpu(d->udev->descriptor.idProduct);
 
 	if (onoff) {
diff --git a/drivers/misc/vmw_vmci/vmci_context.c b/drivers/misc/vmw_vmci/vmci_context.c
index bc089e634a75..26e20b091160 100644
--- a/drivers/misc/vmw_vmci/vmci_context.c
+++ b/drivers/misc/vmw_vmci/vmci_context.c
@@ -751,7 +751,7 @@ static int vmci_ctx_get_chkpt_doorbells(struct vmci_ctx *context,
 			return VMCI_ERROR_MORE_DATA;
 		}
 
-		dbells = kmalloc(data_size, GFP_ATOMIC);
+		dbells = kzalloc(data_size, GFP_ATOMIC);
 		if (!dbells)
 			return VMCI_ERROR_NO_MEM;
 
diff --git a/drivers/net/wireless/marvell/mwifiex/join.c b/drivers/net/wireless/marvell/mwifiex/join.c
index d87aeff70cef..c2cb1e711c06 100644
--- a/drivers/net/wireless/marvell/mwifiex/join.c
+++ b/drivers/net/wireless/marvell/mwifiex/join.c
@@ -877,6 +877,8 @@ mwifiex_cmd_802_11_ad_hoc_start(struct mwifiex_private *priv,
 
 	memset(adhoc_start->ssid, 0, IEEE80211_MAX_SSID_LEN);
 
+	if (req_ssid->ssid_len > IEEE80211_MAX_SSID_LEN)
+		req_ssid->ssid_len = IEEE80211_MAX_SSID_LEN;
 	memcpy(adhoc_start->ssid, req_ssid->ssid, req_ssid->ssid_len);
 
 	mwifiex_dbg(adapter, INFO, "info: ADHOC_S_CMD: SSID = %s\n",
diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c
index 8eb2b6dd36fe..1d0d9c8d0085 100644
--- a/drivers/rtc/rtc-sun6i.c
+++ b/drivers/rtc/rtc-sun6i.c
@@ -230,7 +230,7 @@ static void __init sun6i_rtc_clk_init(struct device_node *node)
 								300000000);
 	if (IS_ERR(rtc->int_osc)) {
 		pr_crit("Couldn't register the internal oscillator\n");
-		return;
+		goto err;
 	}
 
 	parents[0] = clk_hw_get_name(rtc->int_osc);
@@ -246,7 +246,7 @@ static void __init sun6i_rtc_clk_init(struct device_node *node)
 	rtc->losc = clk_register(NULL, &rtc->hw);
 	if (IS_ERR(rtc->losc)) {
 		pr_crit("Couldn't register the LOSC clock\n");
-		return;
+		goto err_register;
 	}
 
 	of_property_read_string_index(node, "clock-output-names", 1,
@@ -257,7 +257,7 @@ static void __init sun6i_rtc_clk_init(struct device_node *node)
 					  &rtc->lock);
 	if (IS_ERR(rtc->ext_losc)) {
 		pr_crit("Couldn't register the LOSC external gate\n");
-		return;
+		goto err_register;
 	}
 
 	clk_data->num = 2;
@@ -266,6 +266,8 @@ static void __init sun6i_rtc_clk_init(struct device_node *node)
 	of_clk_add_hw_provider(node, of_clk_hw_onecell_get, clk_data);
 	return;
 
+err_register:
+	clk_hw_unregister_fixed_rate(rtc->int_osc);
 err:
 	kfree(clk_data);
 }
diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c
index 487b16ace006..0f70cae1c01e 100644
--- a/drivers/s390/block/dasd_alias.c
+++ b/drivers/s390/block/dasd_alias.c
@@ -462,11 +462,19 @@ static int read_unit_address_configuration(struct dasd_device *device,
 	spin_unlock_irqrestore(&lcu->lock, flags);
 
 	rc = dasd_sleep_on(cqr);
-	if (rc && !suborder_not_supported(cqr)) {
+	if (!rc)
+		goto out;
+
+	if (suborder_not_supported(cqr)) {
+		/* suborder not supported or device unusable for IO */
+		rc = -EOPNOTSUPP;
+	} else {
+		/* IO failed but should be retried */
 		spin_lock_irqsave(&lcu->lock, flags);
 		lcu->flags |= NEED_UAC_UPDATE;
 		spin_unlock_irqrestore(&lcu->lock, flags);
 	}
+out:
 	dasd_kfree_request(cqr, cqr->memdev);
 	return rc;
 }
diff --git a/drivers/usb/serial/digi_acceleport.c b/drivers/usb/serial/digi_acceleport.c
index 2ce39af32cfa..e494ffdc06bc 100644
--- a/drivers/usb/serial/digi_acceleport.c
+++ b/drivers/usb/serial/digi_acceleport.c
@@ -23,7 +23,6 @@
 #include <linux/tty_flip.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
-#include <linux/workqueue.h>
 #include <linux/uaccess.h>
 #include <linux/usb.h>
 #include <linux/wait.h>
@@ -202,14 +201,12 @@ struct digi_port {
 	int dp_throttle_restart;
 	wait_queue_head_t dp_flush_wait;
 	wait_queue_head_t dp_close_wait;	/* wait queue for close */
-	struct work_struct dp_wakeup_work;
 	struct usb_serial_port *dp_port;
 };
 
 
 /* Local Function Declarations */
 
-static void digi_wakeup_write_lock(struct work_struct *work);
 static int digi_write_oob_command(struct usb_serial_port *port,
 	unsigned char *buf, int count, int interruptible);
 static int digi_write_inb_command(struct usb_serial_port *port,
@@ -360,26 +357,6 @@ __releases(lock)
 	return timeout;
 }
 
-
-/*
- *  Digi Wakeup Write
- *
- *  Wake up port, line discipline, and tty processes sleeping
- *  on writes.
- */
-
-static void digi_wakeup_write_lock(struct work_struct *work)
-{
-	struct digi_port *priv =
-			container_of(work, struct digi_port, dp_wakeup_work);
-	struct usb_serial_port *port = priv->dp_port;
-	unsigned long flags;
-
-	spin_lock_irqsave(&priv->dp_port_lock, flags);
-	tty_port_tty_wakeup(&port->port);
-	spin_unlock_irqrestore(&priv->dp_port_lock, flags);
-}
-
 /*
  *  Digi Write OOB Command
  *
@@ -990,6 +967,7 @@ static void digi_write_bulk_callback(struct urb *urb)
 	struct digi_serial *serial_priv;
 	int ret = 0;
 	int status = urb->status;
+	bool wakeup;
 
 	/* port and serial sanity check */
 	if (port == NULL || (priv = usb_get_serial_port_data(port)) == NULL) {
@@ -1016,6 +994,7 @@ static void digi_write_bulk_callback(struct urb *urb)
 	}
 
 	/* try to send any buffered data on this port */
+	wakeup = true;
 	spin_lock(&priv->dp_port_lock);
 	priv->dp_write_urb_in_use = 0;
 	if (priv->dp_out_buf_len > 0) {
@@ -1031,19 +1010,18 @@ static void digi_write_bulk_callback(struct urb *urb)
 		if (ret == 0) {
 			priv->dp_write_urb_in_use = 1;
 			priv->dp_out_buf_len = 0;
+			wakeup = false;
 		}
 	}
-	/* wake up processes sleeping on writes immediately */
-	tty_port_tty_wakeup(&port->port);
-	/* also queue up a wakeup at scheduler time, in case we */
-	/* lost the race in write_chan(). */
-	schedule_work(&priv->dp_wakeup_work);
-
 	spin_unlock(&priv->dp_port_lock);
+
 	if (ret && ret != -EPERM)
 		dev_err_console(port,
 			"%s: usb_submit_urb failed, ret=%d, port=%d\n",
 			__func__, ret, priv->dp_port_num);
+
+	if (wakeup)
+		tty_port_tty_wakeup(&port->port);
 }
 
 static int digi_write_room(struct tty_struct *tty)
@@ -1243,7 +1221,6 @@ static int digi_port_init(struct usb_serial_port *port, unsigned port_num)
 	init_waitqueue_head(&priv->dp_transmit_idle_wait);
 	init_waitqueue_head(&priv->dp_flush_wait);
 	init_waitqueue_head(&priv->dp_close_wait);
-	INIT_WORK(&priv->dp_wakeup_work, digi_wakeup_write_lock);
 	priv->dp_port = port;
 
 	init_waitqueue_head(&port->write_wait);
@@ -1510,13 +1487,14 @@ static int digi_read_oob_callback(struct urb *urb)
 			rts = C_CRTSCTS(tty);
 
 		if (tty && opcode == DIGI_CMD_READ_INPUT_SIGNALS) {
+			bool wakeup = false;
+
 			spin_lock(&priv->dp_port_lock);
 			/* convert from digi flags to termiox flags */
 			if (val & DIGI_READ_INPUT_SIGNALS_CTS) {
 				priv->dp_modem_signals |= TIOCM_CTS;
-				/* port must be open to use tty struct */
 				if (rts)
-					tty_port_tty_wakeup(&port->port);
+					wakeup = true;
 			} else {
 				priv->dp_modem_signals &= ~TIOCM_CTS;
 				/* port must be open to use tty struct */
@@ -1535,6 +1513,9 @@ static int digi_read_oob_callback(struct urb *urb)
 				priv->dp_modem_signals &= ~TIOCM_CD;
 
 			spin_unlock(&priv->dp_port_lock);
+
+			if (wakeup)
+				tty_port_tty_wakeup(&port->port);
 		} else if (opcode == DIGI_CMD_TRANSMIT_IDLE) {
 			spin_lock(&priv->dp_port_lock);
 			priv->dp_transmit_idle = 1;
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 6fceefcab81d..dedc7edea517 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -118,8 +118,6 @@ static void vfio_pci_probe_mmaps(struct vfio_pci_device *vdev)
 	int bar;
 	struct vfio_pci_dummy_resource *dummy_res;
 
-	INIT_LIST_HEAD(&vdev->dummy_resources_list);
-
 	for (bar = PCI_STD_RESOURCES; bar <= PCI_STD_RESOURCE_END; bar++) {
 		res = vdev->pdev->resource + bar;
 
@@ -1524,6 +1522,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	vdev->irq_type = VFIO_PCI_NUM_IRQS;
 	mutex_init(&vdev->igate);
 	spin_lock_init(&vdev->irqlock);
+	INIT_LIST_HEAD(&vdev->dummy_resources_list);
 	mutex_init(&vdev->vma_lock);
 	INIT_LIST_HEAD(&vdev->vma_list);
 	init_rwsem(&vdev->memory_lock);
diff --git a/fs/quota/quota_tree.c b/fs/quota/quota_tree.c
index bb3f59bcfcf5..656f9ff63edd 100644
--- a/fs/quota/quota_tree.c
+++ b/fs/quota/quota_tree.c
@@ -61,7 +61,7 @@ static ssize_t read_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf)
 
 	memset(buf, 0, info->dqi_usable_bs);
 	return sb->s_op->quota_read(sb, info->dqi_type, buf,
-	       info->dqi_usable_bs, blk << info->dqi_blocksize_bits);
+	       info->dqi_usable_bs, (loff_t)blk << info->dqi_blocksize_bits);
 }
 
 static ssize_t write_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf)
@@ -70,7 +70,7 @@ static ssize_t write_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf)
 	ssize_t ret;
 
 	ret = sb->s_op->quota_write(sb, info->dqi_type, buf,
-	       info->dqi_usable_bs, blk << info->dqi_blocksize_bits);
+	       info->dqi_usable_bs, (loff_t)blk << info->dqi_blocksize_bits);
 	if (ret != info->dqi_usable_bs) {
 		quota_error(sb, "dquota write failed");
 		if (ret >= 0)
@@ -283,7 +283,7 @@ static uint find_free_dqentry(struct qtree_mem_dqinfo *info,
 			    blk);
 		goto out_buf;
 	}
-	dquot->dq_off = (blk << info->dqi_blocksize_bits) +
+	dquot->dq_off = ((loff_t)blk << info->dqi_blocksize_bits) +
 			sizeof(struct qt_disk_dqdbheader) +
 			i * info->dqi_entry_size;
 	kfree(buf);
@@ -558,7 +558,7 @@ static loff_t find_block_dqentry(struct qtree_mem_dqinfo *info,
 		ret = -EIO;
 		goto out_buf;
 	} else {
-		ret = (blk << info->dqi_blocksize_bits) + sizeof(struct
+		ret = ((loff_t)blk << info->dqi_blocksize_bits) + sizeof(struct
 		  qt_disk_dqdbheader) + i * info->dqi_entry_size;
 	}
 out_buf:
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index 2946713cb00d..5229038852ca 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -454,6 +454,12 @@ static int is_leaf(char *buf, int blocksize, struct buffer_head *bh)
 					 "(second one): %h", ih);
 			return 0;
 		}
+		if (is_direntry_le_ih(ih) && (ih_item_len(ih) < (ih_entry_count(ih) * IH_SIZE))) {
+			reiserfs_warning(NULL, "reiserfs-5093",
+					 "item entry count seems wrong %h",
+					 ih);
+			return 0;
+		}
 		prev_location = ih_location(ih);
 	}
 
diff --git a/include/linux/kdev_t.h b/include/linux/kdev_t.h
index 85b5151911cf..4856706fbfeb 100644
--- a/include/linux/kdev_t.h
+++ b/include/linux/kdev_t.h
@@ -21,61 +21,61 @@
 	})
 
 /* acceptable for old filesystems */
-static inline bool old_valid_dev(dev_t dev)
+static __always_inline bool old_valid_dev(dev_t dev)
 {
 	return MAJOR(dev) < 256 && MINOR(dev) < 256;
 }
 
-static inline u16 old_encode_dev(dev_t dev)
+static __always_inline u16 old_encode_dev(dev_t dev)
 {
 	return (MAJOR(dev) << 8) | MINOR(dev);
 }
 
-static inline dev_t old_decode_dev(u16 val)
+static __always_inline dev_t old_decode_dev(u16 val)
 {
 	return MKDEV((val >> 8) & 255, val & 255);
 }
 
-static inline u32 new_encode_dev(dev_t dev)
+static __always_inline u32 new_encode_dev(dev_t dev)
 {
 	unsigned major = MAJOR(dev);
 	unsigned minor = MINOR(dev);
 	return (minor & 0xff) | (major << 8) | ((minor & ~0xff) << 12);
 }
 
-static inline dev_t new_decode_dev(u32 dev)
+static __always_inline dev_t new_decode_dev(u32 dev)
 {
 	unsigned major = (dev & 0xfff00) >> 8;
 	unsigned minor = (dev & 0xff) | ((dev >> 12) & 0xfff00);
 	return MKDEV(major, minor);
 }
 
-static inline u64 huge_encode_dev(dev_t dev)
+static __always_inline u64 huge_encode_dev(dev_t dev)
 {
 	return new_encode_dev(dev);
 }
 
-static inline dev_t huge_decode_dev(u64 dev)
+static __always_inline dev_t huge_decode_dev(u64 dev)
 {
 	return new_decode_dev(dev);
 }
 
-static inline int sysv_valid_dev(dev_t dev)
+static __always_inline int sysv_valid_dev(dev_t dev)
 {
 	return MAJOR(dev) < (1<<14) && MINOR(dev) < (1<<18);
 }
 
-static inline u32 sysv_encode_dev(dev_t dev)
+static __always_inline u32 sysv_encode_dev(dev_t dev)
 {
 	return MINOR(dev) | (MAJOR(dev) << 18);
 }
 
-static inline unsigned sysv_major(u32 dev)
+static __always_inline unsigned sysv_major(u32 dev)
 {
 	return (dev >> 18) & 0x3fff;
 }
 
-static inline unsigned sysv_minor(u32 dev)
+static __always_inline unsigned sysv_minor(u32 dev)
 {
 	return dev & 0x3ffff;
 }
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 69966c461d1c..882046863581 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -108,7 +108,10 @@ struct lruvec_stat {
  */
 struct mem_cgroup_per_node {
 	struct lruvec		lruvec;
-	struct lruvec_stat __percpu *lruvec_stat;
+
+	struct lruvec_stat __percpu *lruvec_stat_cpu;
+	atomic_long_t		lruvec_stat[NR_VM_NODE_STAT_ITEMS];
+
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 
 	struct mem_cgroup_reclaim_iter	iter[DEF_PRIORITY + 1];
@@ -227,10 +230,10 @@ struct mem_cgroup {
 	spinlock_t		move_lock;
 	struct task_struct	*move_lock_task;
 	unsigned long		move_lock_flags;
-	/*
-	 * percpu counter.
-	 */
-	struct mem_cgroup_stat_cpu __percpu *stat;
+
+	struct mem_cgroup_stat_cpu __percpu *stat_cpu;
+	atomic_long_t		stat[MEMCG_NR_STAT];
+	atomic_long_t		events[MEMCG_NR_EVENTS];
 
 	unsigned long		socket_pressure;
 
@@ -265,6 +268,12 @@ struct mem_cgroup {
 	/* WARNING: nodeinfo must be the last member here */
 };
 
+/*
+ * size of first charge trial. "32" comes from vmscan.c's magic value.
+ * TODO: maybe necessary to use big numbers in big irons.
+ */
+#define MEMCG_CHARGE_BATCH 32U
+
 extern struct mem_cgroup *root_mem_cgroup;
 
 static inline bool mem_cgroup_disabled(void)
@@ -272,13 +281,6 @@ static inline bool mem_cgroup_disabled(void)
 	return !cgroup_subsys_enabled(memory_cgrp_subsys);
 }
 
-static inline void mem_cgroup_event(struct mem_cgroup *memcg,
-				    enum memcg_event_item event)
-{
-	this_cpu_inc(memcg->stat->events[event]);
-	cgroup_file_notify(&memcg->events_file);
-}
-
 bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg);
 
 int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
@@ -492,32 +494,38 @@ void unlock_page_memcg(struct page *page);
 static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
 					     int idx)
 {
-	long val = 0;
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		val += per_cpu(memcg->stat->count[idx], cpu);
-
-	if (val < 0)
-		val = 0;
-
-	return val;
+	long x = atomic_long_read(&memcg->stat[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 /* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void __mod_memcg_state(struct mem_cgroup *memcg,
 				     int idx, int val)
 {
-	if (!mem_cgroup_disabled())
-		__this_cpu_add(memcg->stat->count[idx], val);
+	long x;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	x = val + __this_cpu_read(memcg->stat_cpu->count[idx]);
+	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+		atomic_long_add(x, &memcg->stat[idx]);
+		x = 0;
+	}
+	__this_cpu_write(memcg->stat_cpu->count[idx], x);
 }
 
 /* idx can be of type enum memcg_stat_item or node_stat_item */
 static inline void mod_memcg_state(struct mem_cgroup *memcg,
 				   int idx, int val)
 {
-	if (!mem_cgroup_disabled())
-		this_cpu_add(memcg->stat->count[idx], val);
+	preempt_disable();
+	__mod_memcg_state(memcg, idx, val);
+	preempt_enable();
 }
 
 /**
@@ -555,87 +563,108 @@ static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
 					      enum node_stat_item idx)
 {
 	struct mem_cgroup_per_node *pn;
-	long val = 0;
-	int cpu;
+	long x;
 
 	if (mem_cgroup_disabled())
 		return node_page_state(lruvec_pgdat(lruvec), idx);
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	for_each_possible_cpu(cpu)
-		val += per_cpu(pn->lruvec_stat->count[idx], cpu);
-
-	if (val < 0)
-		val = 0;
-
-	return val;
+	x = atomic_long_read(&pn->lruvec_stat[idx]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
 }
 
 static inline void __mod_lruvec_state(struct lruvec *lruvec,
 				      enum node_stat_item idx, int val)
 {
 	struct mem_cgroup_per_node *pn;
+	long x;
 
+	/* Update node */
 	__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+
 	if (mem_cgroup_disabled())
 		return;
+
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+
+	/* Update memcg */
 	__mod_memcg_state(pn->memcg, idx, val);
-	__this_cpu_add(pn->lruvec_stat->count[idx], val);
+
+	/* Update lruvec */
+	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
+	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+		atomic_long_add(x, &pn->lruvec_stat[idx]);
+		x = 0;
+	}
+	__this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
 }
 
 static inline void mod_lruvec_state(struct lruvec *lruvec,
 				    enum node_stat_item idx, int val)
 {
-	struct mem_cgroup_per_node *pn;
-
-	mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
-	if (mem_cgroup_disabled())
-		return;
-	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	mod_memcg_state(pn->memcg, idx, val);
-	this_cpu_add(pn->lruvec_stat->count[idx], val);
+	preempt_disable();
+	__mod_lruvec_state(lruvec, idx, val);
+	preempt_enable();
 }
 
 static inline void __mod_lruvec_page_state(struct page *page,
 					   enum node_stat_item idx, int val)
 {
-	struct mem_cgroup_per_node *pn;
+	pg_data_t *pgdat = page_pgdat(page);
+	struct lruvec *lruvec;
 
-	__mod_node_page_state(page_pgdat(page), idx, val);
-	if (mem_cgroup_disabled() || !page->mem_cgroup)
+	/* Untracked pages have no memcg, no lruvec. Update only the node */
+	if (!page->mem_cgroup) {
+		__mod_node_page_state(pgdat, idx, val);
 		return;
-	__mod_memcg_state(page->mem_cgroup, idx, val);
-	pn = page->mem_cgroup->nodeinfo[page_to_nid(page)];
-	__this_cpu_add(pn->lruvec_stat->count[idx], val);
+	}
+
+	lruvec = mem_cgroup_lruvec(pgdat, page->mem_cgroup);
+	__mod_lruvec_state(lruvec, idx, val);
 }
 
 static inline void mod_lruvec_page_state(struct page *page,
 					 enum node_stat_item idx, int val)
 {
-	struct mem_cgroup_per_node *pn;
-
-	mod_node_page_state(page_pgdat(page), idx, val);
-	if (mem_cgroup_disabled() || !page->mem_cgroup)
-		return;
-	mod_memcg_state(page->mem_cgroup, idx, val);
-	pn = page->mem_cgroup->nodeinfo[page_to_nid(page)];
-	this_cpu_add(pn->lruvec_stat->count[idx], val);
+	preempt_disable();
+	__mod_lruvec_page_state(page, idx, val);
+	preempt_enable();
 }
 
 unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 						gfp_t gfp_mask,
 						unsigned long *total_scanned);
 
+/* idx can be of type enum memcg_event_item or vm_event_item */
+static inline void __count_memcg_events(struct mem_cgroup *memcg,
+					int idx, unsigned long count)
+{
+	unsigned long x;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	x = count + __this_cpu_read(memcg->stat_cpu->events[idx]);
+	if (unlikely(x > MEMCG_CHARGE_BATCH)) {
+		atomic_long_add(x, &memcg->events[idx]);
+		x = 0;
+	}
+	__this_cpu_write(memcg->stat_cpu->events[idx], x);
+}
+
 static inline void count_memcg_events(struct mem_cgroup *memcg,
-				      enum vm_event_item idx,
-				      unsigned long count)
+				      int idx, unsigned long count)
 {
-	if (!mem_cgroup_disabled())
-		this_cpu_add(memcg->stat->events[idx], count);
+	preempt_disable();
+	__count_memcg_events(memcg, idx, count);
+	preempt_enable();
 }
 
-/* idx can be of type enum memcg_stat_item or node_stat_item */
+/* idx can be of type enum memcg_event_item or vm_event_item */
 static inline void count_memcg_page_event(struct page *page,
 					  int idx)
 {
@@ -654,12 +683,20 @@ static inline void count_memcg_event_mm(struct mm_struct *mm,
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
 	if (likely(memcg)) {
-		this_cpu_inc(memcg->stat->events[idx]);
+		count_memcg_events(memcg, idx, 1);
 		if (idx == OOM_KILL)
 			cgroup_file_notify(&memcg->events_file);
 	}
 	rcu_read_unlock();
 }
+
+static inline void mem_cgroup_event(struct mem_cgroup *memcg,
+				    enum memcg_event_item event)
+{
+	count_memcg_events(memcg, event, 1);
+	cgroup_file_notify(&memcg->events_file);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void mem_cgroup_split_huge_fixup(struct page *head);
 #endif
diff --git a/include/linux/of.h b/include/linux/of.h
index 3c108f9be5e7..af1085615922 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -1163,6 +1163,7 @@ static inline int of_get_available_child_count(const struct device_node *np)
 #define _OF_DECLARE(table, name, compat, fn, fn_type)			\
 	static const struct of_device_id __of_table_##name		\
 		__used __section(__##table##_of_table)			\
+		__aligned(__alignof__(struct of_device_id))		\
 		 = { .compatible = compat,				\
 		     .data = (fn == (fn_type)NULL) ? fn : fn  }
 #else
diff --git a/include/uapi/linux/const.h b/include/uapi/linux/const.h
index 92537757590a..dab9f34383e5 100644
--- a/include/uapi/linux/const.h
+++ b/include/uapi/linux/const.h
@@ -25,4 +25,9 @@
 #define _BITUL(x)	(_AC(1,UL) << (x))
 #define _BITULL(x)	(_AC(1,ULL) << (x))
 
+#define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
+#define __ALIGN_KERNEL_MASK(x, mask)	(((x) + (mask)) & ~(mask))
+
+#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
+
 #endif /* !(_LINUX_CONST_H) */
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 9eae13eefc49..1e3f1a43bf1d 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -14,7 +14,7 @@
 #ifndef _UAPI_LINUX_ETHTOOL_H
 #define _UAPI_LINUX_ETHTOOL_H
 
-#include <linux/kernel.h>
+#include <linux/const.h>
 #include <linux/types.h>
 #include <linux/if_ether.h>
 
diff --git a/include/uapi/linux/kernel.h b/include/uapi/linux/kernel.h
index 0ff8f7477847..fadf2db71fe8 100644
--- a/include/uapi/linux/kernel.h
+++ b/include/uapi/linux/kernel.h
@@ -3,13 +3,6 @@
 #define _UAPI_LINUX_KERNEL_H
 
 #include <linux/sysinfo.h>
-
-/*
- * 'kernel.h' contains some often-used function prototypes etc
- */
-#define __ALIGN_KERNEL(x, a)		__ALIGN_KERNEL_MASK(x, (typeof(x))(a) - 1)
-#define __ALIGN_KERNEL_MASK(x, mask)	(((x) + (mask)) & ~(mask))
-
-#define __KERNEL_DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
+#include <linux/const.h>
 
 #endif /* _UAPI_LINUX_KERNEL_H */
diff --git a/include/uapi/linux/lightnvm.h b/include/uapi/linux/lightnvm.h
index 42d1a434af29..0d44ebba0093 100644
--- a/include/uapi/linux/lightnvm.h
+++ b/include/uapi/linux/lightnvm.h
@@ -21,7 +21,7 @@
 #define _UAPI_LINUX_LIGHTNVM_H
 
 #ifdef __KERNEL__
-#include <linux/kernel.h>
+#include <linux/const.h>
 #include <linux/ioctl.h>
 #else /* __KERNEL__ */
 #include <stdio.h>
diff --git a/include/uapi/linux/mroute6.h b/include/uapi/linux/mroute6.h
index 9999cc006390..1617eb9949a5 100644
--- a/include/uapi/linux/mroute6.h
+++ b/include/uapi/linux/mroute6.h
@@ -2,7 +2,7 @@
 #ifndef _UAPI__LINUX_MROUTE6_H
 #define _UAPI__LINUX_MROUTE6_H
 
-#include <linux/kernel.h>
+#include <linux/const.h>
 #include <linux/types.h>
 #include <linux/sockios.h>
 #include <linux/in6.h>		/* For struct sockaddr_in6. */
diff --git a/include/uapi/linux/netfilter/x_tables.h b/include/uapi/linux/netfilter/x_tables.h
index a8283f7dbc51..b8c6bb233ac1 100644
--- a/include/uapi/linux/netfilter/x_tables.h
+++ b/include/uapi/linux/netfilter/x_tables.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _UAPI_X_TABLES_H
 #define _UAPI_X_TABLES_H
-#include <linux/kernel.h>
+#include <linux/const.h>
 #include <linux/types.h>
 
 #define XT_FUNCTION_MAXNAMELEN 30
diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
index 776bc92e9118..3481cde43a84 100644
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -2,7 +2,7 @@
 #ifndef _UAPI__LINUX_NETLINK_H
 #define _UAPI__LINUX_NETLINK_H
 
-#include <linux/kernel.h>
+#include <linux/const.h>
 #include <linux/socket.h> /* for __kernel_sa_family_t */
 #include <linux/types.h>
 
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index 0f272818a4d2..5fc0b7fd0847 100644
--- a/include/uapi/linux/sysctl.h
+++ b/include/uapi/linux/sysctl.h
@@ -23,7 +23,7 @@
 #ifndef _UAPI_LINUX_SYSCTL_H
 #define _UAPI_LINUX_SYSCTL_H
 
-#include <linux/kernel.h>
+#include <linux/const.h>
 #include <linux/types.h>
 #include <linux/compiler.h>
 
diff --git a/kernel/module.c b/kernel/module.c
index 2806c9b6577c..0b2654592d3a 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1789,7 +1789,6 @@ static int mod_sysfs_init(struct module *mod)
 	if (err)
 		mod_kobject_put(mod);
 
-	/* delay uevent until full sysfs population */
 out:
 	return err;
 }
@@ -1826,7 +1825,6 @@ static int mod_sysfs_setup(struct module *mod,
 	add_sect_attrs(mod, info);
 	add_notes_attrs(mod, info);
 
-	kobject_uevent(&mod->mkobj.kobj, KOBJ_ADD);
 	return 0;
 
 out_unreg_modinfo_attrs:
@@ -3481,6 +3479,9 @@ static noinline int do_init_module(struct module *mod)
 	blocking_notifier_call_chain(&module_notify_list,
 				     MODULE_STATE_LIVE, mod);
 
+	/* Delay uevent until module has finished its init routine */
+	kobject_uevent(&mod->mkobj.kobj, KOBJ_ADD);
+
 	/*
 	 * We need to finish all async code before the module init sequence
 	 * is done.  This has potential to deadlock.  For example, a newly
@@ -3801,6 +3802,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
 				     MODULE_STATE_GOING, mod);
 	klp_module_going(mod);
  bug_cleanup:
+	mod->state = MODULE_STATE_GOING;
 	/* module_bug_cleanup needs module_mutex protection */
 	mutex_lock(&module_mutex);
 	module_bug_cleanup(mod);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 70707d44a690..4e763cdccb33 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -542,39 +542,10 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
 	return mz;
 }
 
-/*
- * Return page count for single (non recursive) @memcg.
- *
- * Implementation Note: reading percpu statistics for memcg.
- *
- * Both of vmstat[] and percpu_counter has threshold and do periodic
- * synchronization to implement "quick" read. There are trade-off between
- * reading cost and precision of value. Then, we may have a chance to implement
- * a periodic synchronization of counter in memcg's counter.
- *
- * But this _read() function is used for user interface now. The user accounts
- * memory usage by memory cgroup and he _always_ requires exact value because
- * he accounts memory. Even if we provide quick-and-fuzzy read, we always
- * have to visit all online cpus and make sum. So, for now, unnecessary
- * synchronization is not implemented. (just implemented for cpu hotplug)
- *
- * If there are kernel internal actions which can make use of some not-exact
- * value, and reading all cpu value can be performance bottleneck in some
- * common workload, threshold and synchronization as vmstat[] should be
- * implemented.
- *
- * The parameter idx can be of type enum memcg_event_item or vm_event_item.
- */
-
 static unsigned long memcg_sum_events(struct mem_cgroup *memcg,
 				      int event)
 {
-	unsigned long val = 0;
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		val += per_cpu(memcg->stat->events[event], cpu);
-	return val;
+	return atomic_long_read(&memcg->events[event]);
 }
 
 static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
@@ -586,27 +557,27 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
 	 * counted as CACHE even if it's on ANON LRU.
 	 */
 	if (PageAnon(page))
-		__this_cpu_add(memcg->stat->count[MEMCG_RSS], nr_pages);
+		__mod_memcg_state(memcg, MEMCG_RSS, nr_pages);
 	else {
-		__this_cpu_add(memcg->stat->count[MEMCG_CACHE], nr_pages);
+		__mod_memcg_state(memcg, MEMCG_CACHE, nr_pages);
 		if (PageSwapBacked(page))
-			__this_cpu_add(memcg->stat->count[NR_SHMEM], nr_pages);
+			__mod_memcg_state(memcg, NR_SHMEM, nr_pages);
 	}
 
 	if (compound) {
 		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
-		__this_cpu_add(memcg->stat->count[MEMCG_RSS_HUGE], nr_pages);
+		__mod_memcg_state(memcg, MEMCG_RSS_HUGE, nr_pages);
 	}
 
 	/* pagein of a big page is an event. So, ignore page size */
 	if (nr_pages > 0)
-		__this_cpu_inc(memcg->stat->events[PGPGIN]);
+		__count_memcg_events(memcg, PGPGIN, 1);
 	else {
-		__this_cpu_inc(memcg->stat->events[PGPGOUT]);
+		__count_memcg_events(memcg, PGPGOUT, 1);
 		nr_pages = -nr_pages; /* for event */
 	}
 
-	__this_cpu_add(memcg->stat->nr_page_events, nr_pages);
+	__this_cpu_add(memcg->stat_cpu->nr_page_events, nr_pages);
 }
 
 unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
@@ -642,8 +613,8 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
 {
 	unsigned long val, next;
 
-	val = __this_cpu_read(memcg->stat->nr_page_events);
-	next = __this_cpu_read(memcg->stat->targets[target]);
+	val = __this_cpu_read(memcg->stat_cpu->nr_page_events);
+	next = __this_cpu_read(memcg->stat_cpu->targets[target]);
 	/* from time_after() in jiffies.h */
 	if ((long)(next - val) < 0) {
 		switch (target) {
@@ -659,7 +630,7 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
 		default:
 			break;
 		}
-		__this_cpu_write(memcg->stat->targets[target], next);
+		__this_cpu_write(memcg->stat_cpu->targets[target], next);
 		return true;
 	}
 	return false;
@@ -1726,11 +1697,6 @@ void unlock_page_memcg(struct page *page)
 }
 EXPORT_SYMBOL(unlock_page_memcg);
 
-/*
- * size of first charge trial. "32" comes from vmscan.c's magic value.
- * TODO: maybe necessary to use big numbers in big irons.
- */
-#define CHARGE_BATCH	32U
 struct memcg_stock_pcp {
 	struct mem_cgroup *cached; /* this never be root cgroup */
 	unsigned int nr_pages;
@@ -1758,7 +1724,7 @@ static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 	unsigned long flags;
 	bool ret = false;
 
-	if (nr_pages > CHARGE_BATCH)
+	if (nr_pages > MEMCG_CHARGE_BATCH)
 		return ret;
 
 	local_irq_save(flags);
@@ -1827,7 +1793,7 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 	}
 	stock->nr_pages += nr_pages;
 
-	if (stock->nr_pages > CHARGE_BATCH)
+	if (stock->nr_pages > MEMCG_CHARGE_BATCH)
 		drain_stock(stock);
 
 	local_irq_restore(flags);
@@ -1877,9 +1843,44 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
 static int memcg_hotplug_cpu_dead(unsigned int cpu)
 {
 	struct memcg_stock_pcp *stock;
+	struct mem_cgroup *memcg;
 
 	stock = &per_cpu(memcg_stock, cpu);
 	drain_stock(stock);
+
+	for_each_mem_cgroup(memcg) {
+		int i;
+
+		for (i = 0; i < MEMCG_NR_STAT; i++) {
+			int nid;
+			long x;
+
+			x = this_cpu_xchg(memcg->stat_cpu->count[i], 0);
+			if (x)
+				atomic_long_add(x, &memcg->stat[i]);
+
+			if (i >= NR_VM_NODE_STAT_ITEMS)
+				continue;
+
+			for_each_node(nid) {
+				struct mem_cgroup_per_node *pn;
+
+				pn = mem_cgroup_nodeinfo(memcg, nid);
+				x = this_cpu_xchg(pn->lruvec_stat_cpu->count[i], 0);
+				if (x)
+					atomic_long_add(x, &pn->lruvec_stat[i]);
+			}
+		}
+
+		for (i = 0; i < MEMCG_NR_EVENTS; i++) {
+			long x;
+
+			x = this_cpu_xchg(memcg->stat_cpu->events[i], 0);
+			if (x)
+				atomic_long_add(x, &memcg->events[i]);
+		}
+	}
+
 	return 0;
 }
 
@@ -1900,7 +1901,7 @@ static void high_work_func(struct work_struct *work)
 	struct mem_cgroup *memcg;
 
 	memcg = container_of(work, struct mem_cgroup, high_work);
-	reclaim_high(memcg, CHARGE_BATCH, GFP_KERNEL);
+	reclaim_high(memcg, MEMCG_CHARGE_BATCH, GFP_KERNEL);
 }
 
 /*
@@ -1924,7 +1925,7 @@ void mem_cgroup_handle_over_high(void)
 static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 		      unsigned int nr_pages)
 {
-	unsigned int batch = max(CHARGE_BATCH, nr_pages);
+	unsigned int batch = max(MEMCG_CHARGE_BATCH, nr_pages);
 	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
 	struct mem_cgroup *mem_over_limit;
 	struct page_counter *counter;
@@ -2444,18 +2445,11 @@ void mem_cgroup_split_huge_fixup(struct page *head)
 	for (i = 1; i < HPAGE_PMD_NR; i++)
 		head[i].mem_cgroup = head->mem_cgroup;
 
-	__this_cpu_sub(head->mem_cgroup->stat->count[MEMCG_RSS_HUGE],
-		       HPAGE_PMD_NR);
+	__mod_memcg_state(head->mem_cgroup, MEMCG_RSS_HUGE, -HPAGE_PMD_NR);
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #ifdef CONFIG_MEMCG_SWAP
-static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg,
-				       int nr_entries)
-{
-	this_cpu_add(memcg->stat->count[MEMCG_SWAP], nr_entries);
-}
-
 /**
  * mem_cgroup_move_swap_account - move swap charge and swap_cgroup's record.
  * @entry: swap entry to be moved
@@ -2479,8 +2473,8 @@ static int mem_cgroup_move_swap_account(swp_entry_t entry,
 	new_id = mem_cgroup_id(to);
 
 	if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) {
-		mem_cgroup_swap_statistics(from, -1);
-		mem_cgroup_swap_statistics(to, 1);
+		mod_memcg_state(from, MEMCG_SWAP, -1);
+		mod_memcg_state(to, MEMCG_SWAP, 1);
 		return 0;
 	}
 	return -EINVAL;
@@ -4210,8 +4204,8 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 	if (!pn)
 		return 1;
 
-	pn->lruvec_stat = alloc_percpu(struct lruvec_stat);
-	if (!pn->lruvec_stat) {
+	pn->lruvec_stat_cpu = alloc_percpu(struct lruvec_stat);
+	if (!pn->lruvec_stat_cpu) {
 		kfree(pn);
 		return 1;
 	}
@@ -4232,7 +4226,7 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 	if (!pn)
 		return;
 
-	free_percpu(pn->lruvec_stat);
+	free_percpu(pn->lruvec_stat_cpu);
 	kfree(pn);
 }
 
@@ -4242,7 +4236,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 
 	for_each_node(node)
 		free_mem_cgroup_per_node_info(memcg, node);
-	free_percpu(memcg->stat);
+	free_percpu(memcg->stat_cpu);
 	kfree(memcg);
 }
 
@@ -4271,8 +4265,8 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	if (memcg->id.id < 0)
 		goto fail;
 
-	memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu);
-	if (!memcg->stat)
+	memcg->stat_cpu = alloc_percpu(struct mem_cgroup_stat_cpu);
+	if (!memcg->stat_cpu)
 		goto fail;
 
 	for_each_node(node)
@@ -4632,8 +4626,8 @@ static int mem_cgroup_move_account(struct page *page,
 	spin_lock_irqsave(&from->move_lock, flags);
 
 	if (!anon && page_mapped(page)) {
-		__this_cpu_sub(from->stat->count[NR_FILE_MAPPED], nr_pages);
-		__this_cpu_add(to->stat->count[NR_FILE_MAPPED], nr_pages);
+		__mod_memcg_state(from, NR_FILE_MAPPED, -nr_pages);
+		__mod_memcg_state(to, NR_FILE_MAPPED, nr_pages);
 	}
 
 	/*
@@ -4645,16 +4639,14 @@ static int mem_cgroup_move_account(struct page *page,
 		struct address_space *mapping = page_mapping(page);
 
 		if (mapping_cap_account_dirty(mapping)) {
-			__this_cpu_sub(from->stat->count[NR_FILE_DIRTY],
-				       nr_pages);
-			__this_cpu_add(to->stat->count[NR_FILE_DIRTY],
-				       nr_pages);
+			__mod_memcg_state(from, NR_FILE_DIRTY, -nr_pages);
+			__mod_memcg_state(to, NR_FILE_DIRTY, nr_pages);
 		}
 	}
 
 	if (PageWriteback(page)) {
-		__this_cpu_sub(from->stat->count[NR_WRITEBACK], nr_pages);
-		__this_cpu_add(to->stat->count[NR_WRITEBACK], nr_pages);
+		__mod_memcg_state(from, NR_WRITEBACK, -nr_pages);
+		__mod_memcg_state(to, NR_WRITEBACK, nr_pages);
 	}
 
 	/*
@@ -5690,12 +5682,12 @@ static void uncharge_batch(const struct uncharge_gather *ug)
 	}
 
 	local_irq_save(flags);
-	__this_cpu_sub(ug->memcg->stat->count[MEMCG_RSS], ug->nr_anon);
-	__this_cpu_sub(ug->memcg->stat->count[MEMCG_CACHE], ug->nr_file);
-	__this_cpu_sub(ug->memcg->stat->count[MEMCG_RSS_HUGE], ug->nr_huge);
-	__this_cpu_sub(ug->memcg->stat->count[NR_SHMEM], ug->nr_shmem);
-	__this_cpu_add(ug->memcg->stat->events[PGPGOUT], ug->pgpgout);
-	__this_cpu_add(ug->memcg->stat->nr_page_events, nr_pages);
+	__mod_memcg_state(ug->memcg, MEMCG_RSS, -ug->nr_anon);
+	__mod_memcg_state(ug->memcg, MEMCG_CACHE, -ug->nr_file);
+	__mod_memcg_state(ug->memcg, MEMCG_RSS_HUGE, -ug->nr_huge);
+	__mod_memcg_state(ug->memcg, NR_SHMEM, -ug->nr_shmem);
+	__count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout);
+	__this_cpu_add(ug->memcg->stat_cpu->nr_page_events, nr_pages);
 	memcg_check_events(ug->memcg, ug->dummy_page);
 	local_irq_restore(flags);
 
@@ -5926,7 +5918,7 @@ bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages)
 	if (in_softirq())
 		gfp_mask = GFP_NOWAIT;
 
-	this_cpu_add(memcg->stat->count[MEMCG_SOCK], nr_pages);
+	mod_memcg_state(memcg, MEMCG_SOCK, nr_pages);
 
 	if (try_charge(memcg, gfp_mask, nr_pages) == 0)
 		return true;
@@ -5947,7 +5939,7 @@ void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages)
 		return;
 	}
 
-	this_cpu_sub(memcg->stat->count[MEMCG_SOCK], nr_pages);
+	mod_memcg_state(memcg, MEMCG_SOCK, -nr_pages);
 
 	refill_stock(memcg, nr_pages);
 }
@@ -6071,7 +6063,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg),
 				   nr_entries);
 	VM_BUG_ON_PAGE(oldid, page);
-	mem_cgroup_swap_statistics(swap_memcg, nr_entries);
+	mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);
 
 	page->mem_cgroup = NULL;
 
@@ -6137,7 +6129,7 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
 		mem_cgroup_id_get_many(memcg, nr_pages - 1);
 	oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg), nr_pages);
 	VM_BUG_ON_PAGE(oldid, page);
-	mem_cgroup_swap_statistics(memcg, nr_pages);
+	mod_memcg_state(memcg, MEMCG_SWAP, nr_pages);
 
 	return 0;
 }
@@ -6165,7 +6157,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages)
 			else
 				page_counter_uncharge(&memcg->memsw, nr_pages);
 		}
-		mem_cgroup_swap_statistics(memcg, -nr_pages);
+		mod_memcg_state(memcg, MEMCG_SWAP, -nr_pages);
 		mem_cgroup_id_put_many(memcg, nr_pages);
 	}
 	rcu_read_unlock();
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 071e09c3d855..c78db361cbba 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -721,8 +721,13 @@ static int snd_pcm_hw_params(struct snd_pcm_substream *substream,
 		runtime->boundary *= 2;
 
 	/* clear the buffer for avoiding possible kernel info leaks */
-	if (runtime->dma_area && !substream->ops->copy_user)
-		memset(runtime->dma_area, 0, runtime->dma_bytes);
+	if (runtime->dma_area && !substream->ops->copy_user) {
+		size_t size = runtime->dma_bytes;
+
+		if (runtime->info & SNDRV_PCM_INFO_MMAP)
+			size = PAGE_ALIGN(size);
+		memset(runtime->dma_area, 0, size);
+	}
 
 	snd_pcm_timer_resolution_change(substream);
 	snd_pcm_set_state(substream, SNDRV_PCM_STATE_SETUP);
diff --git a/sound/core/seq/seq_queue.h b/sound/core/seq/seq_queue.h
index 719093489a2c..7909cf6040e3 100644
--- a/sound/core/seq/seq_queue.h
+++ b/sound/core/seq/seq_queue.h
@@ -40,10 +40,10 @@ struct snd_seq_queue {
 	
 	struct snd_seq_timer *timer;	/* time keeper for this queue */
 	int	owner;		/* client that 'owns' the timer */
-	unsigned int	locked:1,	/* timer is only accesibble by owner if set */
-		klocked:1,	/* kernel lock (after START) */	
-		check_again:1,
-		check_blocked:1;
+	bool	locked;		/* timer is only accesibble by owner if set */
+	bool	klocked;	/* kernel lock (after START) */
+	bool	check_again;	/* concurrent access happened during check */
+	bool	check_blocked;	/* queue being checked */
 
 	unsigned int flags;		/* status flags */
 	unsigned int info_flags;	/* info for sync */
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 92f5f452bee2..369f812d7072 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -4443,11 +4443,10 @@ static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb)
 	/* Delay enabling the HP amp, to let the mic-detection
 	 * state machine run.
 	 */
-	cancel_delayed_work(&spec->unsol_hp_work);
-	schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500));
 	tbl = snd_hda_jack_tbl_get(codec, cb->nid);
 	if (tbl)
 		tbl->block_report = 1;
+	schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500));
 }
 
 static void amic_callback(struct hda_codec *codec, struct hda_jack_callback *cb)
@@ -4625,12 +4624,25 @@ static void ca0132_free(struct hda_codec *codec)
 	kfree(codec->spec);
 }
 
+#ifdef CONFIG_PM
+static int ca0132_suspend(struct hda_codec *codec)
+{
+	struct ca0132_spec *spec = codec->spec;
+
+	cancel_delayed_work_sync(&spec->unsol_hp_work);
+	return 0;
+}
+#endif
+
 static const struct hda_codec_ops ca0132_patch_ops = {
 	.build_controls = ca0132_build_controls,
 	.build_pcms = ca0132_build_pcms,
 	.init = ca0132_init,
 	.free = ca0132_free,
 	.unsol_event = snd_hda_jack_unsol_event,
+#ifdef CONFIG_PM
+	.suspend = ca0132_suspend,
+#endif
 };
 
 static void ca0132_config(struct hda_codec *codec)
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 6caf94581a0e..ecdbdb26164e 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -324,6 +324,7 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs,
 	struct usb_host_interface *alts;
 	struct usb_interface *iface;
 	unsigned int ep;
+	unsigned int ifnum;
 
 	/* Implicit feedback sync EPs consumers are always playback EPs */
 	if (subs->direction != SNDRV_PCM_STREAM_PLAYBACK)
@@ -334,44 +335,23 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs,
 	case USB_ID(0x0763, 0x2031): /* M-Audio Fast Track C600 */
 	case USB_ID(0x22f0, 0x0006): /* Allen&Heath Qu-16 */
 		ep = 0x81;
-		iface = usb_ifnum_to_if(dev, 3);
-
-		if (!iface || iface->num_altsetting == 0)
-			return -EINVAL;
-
-		alts = &iface->altsetting[1];
-		goto add_sync_ep;
-		break;
+		ifnum = 3;
+		goto add_sync_ep_from_ifnum;
 	case USB_ID(0x0763, 0x2080): /* M-Audio FastTrack Ultra */
 	case USB_ID(0x0763, 0x2081):
 		ep = 0x81;
-		iface = usb_ifnum_to_if(dev, 2);
-
-		if (!iface || iface->num_altsetting == 0)
-			return -EINVAL;
-
-		alts = &iface->altsetting[1];
-		goto add_sync_ep;
-	case USB_ID(0x2466, 0x8003):
+		ifnum = 2;
+		goto add_sync_ep_from_ifnum;
+	case USB_ID(0x2466, 0x8003): /* Fractal Audio Axe-Fx II */
 		ep = 0x86;
-		iface = usb_ifnum_to_if(dev, 2);
-
-		if (!iface || iface->num_altsetting == 0)
-			return -EINVAL;
-
-		alts = &iface->altsetting[1];
-		goto add_sync_ep;
-	case USB_ID(0x1397, 0x0002):
+		ifnum = 2;
+		goto add_sync_ep_from_ifnum;
+	case USB_ID(0x1397, 0x0002): /* Behringer UFX1204 */
 		ep = 0x81;
-		iface = usb_ifnum_to_if(dev, 1);
-
-		if (!iface || iface->num_altsetting == 0)
-			return -EINVAL;
-
-		alts = &iface->altsetting[1];
-		goto add_sync_ep;
-
+		ifnum = 1;
+		goto add_sync_ep_from_ifnum;
 	}
+
 	if (attr == USB_ENDPOINT_SYNC_ASYNC &&
 	    altsd->bInterfaceClass == USB_CLASS_VENDOR_SPEC &&
 	    altsd->bInterfaceProtocol == 2 &&
@@ -386,6 +366,14 @@ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs,
 	/* No quirk */
 	return 0;
 
+add_sync_ep_from_ifnum:
+	iface = usb_ifnum_to_if(dev, ifnum);
+
+	if (!iface || iface->num_altsetting < 2)
+		return -EINVAL;
+
+	alts = &iface->altsetting[1];
+
 add_sync_ep:
 	subs->sync_endpoint = snd_usb_add_endpoint(subs->stream->chip,
 						   alts, ep, !subs->direction,