Merge branch 'akpm' (updates from Andrew Morton)

Merge misc fixes from Andrew Morton:
 "Bunch of fixes and one little addition to math64.h"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (27 commits)
  include/linux/math64.h: add div64_ul()
  mm: memcontrol: fix lockless reclaim hierarchy iterator
  frontswap: fix incorrect zeroing and allocation size for frontswap_map
  kernel/audit_tree.c:audit_add_tree_rule(): protect `rule' from kill_rules()
  mm: migration: add migrate_entry_wait_huge()
  ocfs2: add missing lockres put in dlm_mig_lockres_handler
  mm/page_alloc.c: fix watermark check in __zone_watermark_ok()
  drivers/misc/sgi-gru/grufile.c: fix info leak in gru_get_config_info()
  aio: fix io_destroy() regression by using call_rcu()
  rtc-at91rm9200: use shadow IMR on at91sam9x5
  rtc-at91rm9200: add shadow interrupt mask
  rtc-at91rm9200: refactor interrupt-register handling
  rtc-at91rm9200: add configuration support
  rtc-at91rm9200: add match-table compile guard
  fs/ocfs2/namei.c: remove unecessary ERROR when removing non-empty directory
  swap: avoid read_swap_cache_async() race to deadlock while waiting on discard I/O completion
  drivers/rtc/rtc-twl.c: fix missing device_init_wakeup() when booted with device tree
  cciss: fix broken mutex usage in ioctl
  audit: wait_for_auditd() should use TASK_UNINTERRUPTIBLE
  drivers/rtc/rtc-cmos.c: fix accidentally enabling rtc channel
  ...

28 files changed, 321 insertions, 168 deletions

diff --git a/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.txt b/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.txt
index 2a3feabd3b22..34c1505774bf 100644
--- a/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.txt
+++ b/Documentation/devicetree/bindings/rtc/atmel,at91rm9200-rtc.txt
@@ -1,7 +1,7 @@
 Atmel AT91RM9200 Real Time Clock
 
 Required properties:
-- compatible: should be: "atmel,at91rm9200-rtc"
+- compatible: should be: "atmel,at91rm9200-rtc" or "atmel,at91sam9x5-rtc"
 - reg: physical base address of the controller and length of memory mapped
   region.
 - interrupts: rtc alarm/event interrupt
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 6374dc103521..62b6c2cc80b5 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -168,8 +168,6 @@ static irqreturn_t do_cciss_msix_intr(int irq, void *dev_id);
 static int cciss_open(struct block_device *bdev, fmode_t mode);
 static int cciss_unlocked_open(struct block_device *bdev, fmode_t mode);
 static void cciss_release(struct gendisk *disk, fmode_t mode);
-static int do_ioctl(struct block_device *bdev, fmode_t mode,
-		    unsigned int cmd, unsigned long arg);
 static int cciss_ioctl(struct block_device *bdev, fmode_t mode,
 		       unsigned int cmd, unsigned long arg);
 static int cciss_getgeo(struct block_device *bdev, struct hd_geometry *geo);
@@ -235,7 +233,7 @@ static const struct block_device_operations cciss_fops = {
 	.owner = THIS_MODULE,
 	.open = cciss_unlocked_open,
 	.release = cciss_release,
-	.ioctl = do_ioctl,
+	.ioctl = cciss_ioctl,
 	.getgeo = cciss_getgeo,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = cciss_compat_ioctl,
@@ -1143,16 +1141,6 @@ static void cciss_release(struct gendisk *disk, fmode_t mode)
 	mutex_unlock(&cciss_mutex);
 }
 
-static int do_ioctl(struct block_device *bdev, fmode_t mode,
-		    unsigned cmd, unsigned long arg)
-{
-	int ret;
-	mutex_lock(&cciss_mutex);
-	ret = cciss_ioctl(bdev, mode, cmd, arg);
-	mutex_unlock(&cciss_mutex);
-	return ret;
-}
-
 #ifdef CONFIG_COMPAT
 
 static int cciss_ioctl32_passthru(struct block_device *bdev, fmode_t mode,
@@ -1179,7 +1167,7 @@ static int cciss_compat_ioctl(struct block_device *bdev, fmode_t mode,
 	case CCISS_REGNEWD:
 	case CCISS_RESCANDISK:
 	case CCISS_GETLUNINFO:
-		return do_ioctl(bdev, mode, cmd, arg);
+		return cciss_ioctl(bdev, mode, cmd, arg);
 
 	case CCISS_PASSTHRU32:
 		return cciss_ioctl32_passthru(bdev, mode, cmd, arg);
@@ -1219,7 +1207,7 @@ static int cciss_ioctl32_passthru(struct block_device *bdev, fmode_t mode,
 	if (err)
 		return -EFAULT;
 
-	err = do_ioctl(bdev, mode, CCISS_PASSTHRU, (unsigned long)p);
+	err = cciss_ioctl(bdev, mode, CCISS_PASSTHRU, (unsigned long)p);
 	if (err)
 		return err;
 	err |=
@@ -1261,7 +1249,7 @@ static int cciss_ioctl32_big_passthru(struct block_device *bdev, fmode_t mode,
 	if (err)
 		return -EFAULT;
 
-	err = do_ioctl(bdev, mode, CCISS_BIG_PASSTHRU, (unsigned long)p);
+	err = cciss_ioctl(bdev, mode, CCISS_BIG_PASSTHRU, (unsigned long)p);
 	if (err)
 		return err;
 	err |=
@@ -1311,11 +1299,14 @@ static int cciss_getpciinfo(ctlr_info_t *h, void __user *argp)
 static int cciss_getintinfo(ctlr_info_t *h, void __user *argp)
 {
 	cciss_coalint_struct intinfo;
+	unsigned long flags;
 
 	if (!argp)
 		return -EINVAL;
+	spin_lock_irqsave(&h->lock, flags);
 	intinfo.delay = readl(&h->cfgtable->HostWrite.CoalIntDelay);
 	intinfo.count = readl(&h->cfgtable->HostWrite.CoalIntCount);
+	spin_unlock_irqrestore(&h->lock, flags);
 	if (copy_to_user
 	    (argp, &intinfo, sizeof(cciss_coalint_struct)))
 		return -EFAULT;
@@ -1356,12 +1347,15 @@ static int cciss_setintinfo(ctlr_info_t *h, void __user *argp)
 static int cciss_getnodename(ctlr_info_t *h, void __user *argp)
 {
 	NodeName_type NodeName;
+	unsigned long flags;
 	int i;
 
 	if (!argp)
 		return -EINVAL;
+	spin_lock_irqsave(&h->lock, flags);
 	for (i = 0; i < 16; i++)
 		NodeName[i] = readb(&h->cfgtable->ServerName[i]);
+	spin_unlock_irqrestore(&h->lock, flags);
 	if (copy_to_user(argp, NodeName, sizeof(NodeName_type)))
 		return -EFAULT;
 	return 0;
@@ -1398,10 +1392,13 @@ static int cciss_setnodename(ctlr_info_t *h, void __user *argp)
 static int cciss_getheartbeat(ctlr_info_t *h, void __user *argp)
 {
 	Heartbeat_type heartbeat;
+	unsigned long flags;
 
 	if (!argp)
 		return -EINVAL;
+	spin_lock_irqsave(&h->lock, flags);
 	heartbeat = readl(&h->cfgtable->HeartBeat);
+	spin_unlock_irqrestore(&h->lock, flags);
 	if (copy_to_user(argp, &heartbeat, sizeof(Heartbeat_type)))
 		return -EFAULT;
 	return 0;
@@ -1410,10 +1407,13 @@ static int cciss_getheartbeat(ctlr_info_t *h, void __user *argp)
 static int cciss_getbustypes(ctlr_info_t *h, void __user *argp)
 {
 	BusTypes_type BusTypes;
+	unsigned long flags;
 
 	if (!argp)
 		return -EINVAL;
+	spin_lock_irqsave(&h->lock, flags);
 	BusTypes = readl(&h->cfgtable->BusTypes);
+	spin_unlock_irqrestore(&h->lock, flags);
 	if (copy_to_user(argp, &BusTypes, sizeof(BusTypes_type)))
 		return -EFAULT;
 	return 0;
diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c
index 44d273c5e19d..0535d1e0bc78 100644
--- a/drivers/misc/sgi-gru/grufile.c
+++ b/drivers/misc/sgi-gru/grufile.c
@@ -172,6 +172,7 @@ static long gru_get_config_info(unsigned long arg)
 		nodesperblade = 2;
 	else
 		nodesperblade = 1;
+	memset(&info, 0, sizeof(info));
 	info.cpus = num_online_cpus();
 	info.nodes = num_online_nodes();
 	info.blades = info.nodes / nodesperblade;
diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c
index 0eab77b22340..f296f3f7db9b 100644
--- a/drivers/rtc/rtc-at91rm9200.c
+++ b/drivers/rtc/rtc-at91rm9200.c
@@ -25,6 +25,7 @@
 #include <linux/rtc.h>
 #include <linux/bcd.h>
 #include <linux/interrupt.h>
+#include <linux/spinlock.h>
 #include <linux/ioctl.h>
 #include <linux/completion.h>
 #include <linux/io.h>
@@ -42,10 +43,65 @@
 
 #define AT91_RTC_EPOCH		1900UL	/* just like arch/arm/common/rtctime.c */
 
+struct at91_rtc_config {
+	bool use_shadow_imr;
+};
+
+static const struct at91_rtc_config *at91_rtc_config;
 static DECLARE_COMPLETION(at91_rtc_updated);
 static unsigned int at91_alarm_year = AT91_RTC_EPOCH;
 static void __iomem *at91_rtc_regs;
 static int irq;
+static DEFINE_SPINLOCK(at91_rtc_lock);
+static u32 at91_rtc_shadow_imr;
+
+static void at91_rtc_write_ier(u32 mask)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&at91_rtc_lock, flags);
+	at91_rtc_shadow_imr |= mask;
+	at91_rtc_write(AT91_RTC_IER, mask);
+	spin_unlock_irqrestore(&at91_rtc_lock, flags);
+}
+
+static void at91_rtc_write_idr(u32 mask)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&at91_rtc_lock, flags);
+	at91_rtc_write(AT91_RTC_IDR, mask);
+	/*
+	 * Register read back (of any RTC-register) needed to make sure
+	 * IDR-register write has reached the peripheral before updating
+	 * shadow mask.
+	 *
+	 * Note that there is still a possibility that the mask is updated
+	 * before interrupts have actually been disabled in hardware. The only
+	 * way to be certain would be to poll the IMR-register, which is is
+	 * the very register we are trying to emulate. The register read back
+	 * is a reasonable heuristic.
+	 */
+	at91_rtc_read(AT91_RTC_SR);
+	at91_rtc_shadow_imr &= ~mask;
+	spin_unlock_irqrestore(&at91_rtc_lock, flags);
+}
+
+static u32 at91_rtc_read_imr(void)
+{
+	unsigned long flags;
+	u32 mask;
+
+	if (at91_rtc_config->use_shadow_imr) {
+		spin_lock_irqsave(&at91_rtc_lock, flags);
+		mask = at91_rtc_shadow_imr;
+		spin_unlock_irqrestore(&at91_rtc_lock, flags);
+	} else {
+		mask = at91_rtc_read(AT91_RTC_IMR);
+	}
+
+	return mask;
+}
 
 /*
  * Decode time/date into rtc_time structure
@@ -110,9 +166,9 @@ static int at91_rtc_settime(struct device *dev, struct rtc_time *tm)
 	cr = at91_rtc_read(AT91_RTC_CR);
 	at91_rtc_write(AT91_RTC_CR, cr | AT91_RTC_UPDCAL | AT91_RTC_UPDTIM);
 
-	at91_rtc_write(AT91_RTC_IER, AT91_RTC_ACKUPD);
+	at91_rtc_write_ier(AT91_RTC_ACKUPD);
 	wait_for_completion(&at91_rtc_updated);	/* wait for ACKUPD interrupt */
-	at91_rtc_write(AT91_RTC_IDR, AT91_RTC_ACKUPD);
+	at91_rtc_write_idr(AT91_RTC_ACKUPD);
 
 	at91_rtc_write(AT91_RTC_TIMR,
 			  bin2bcd(tm->tm_sec) << 0
@@ -144,7 +200,7 @@ static int at91_rtc_readalarm(struct device *dev, struct rtc_wkalrm *alrm)
 	tm->tm_yday = rtc_year_days(tm->tm_mday, tm->tm_mon, tm->tm_year);
 	tm->tm_year = at91_alarm_year - 1900;
 
-	alrm->enabled = (at91_rtc_read(AT91_RTC_IMR) & AT91_RTC_ALARM)
+	alrm->enabled = (at91_rtc_read_imr() & AT91_RTC_ALARM)
 			? 1 : 0;
 
 	dev_dbg(dev, "%s(): %4d-%02d-%02d %02d:%02d:%02d\n", __func__,
@@ -169,7 +225,7 @@ static int at91_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
 	tm.tm_min = alrm->time.tm_min;
 	tm.tm_sec = alrm->time.tm_sec;
 
-	at91_rtc_write(AT91_RTC_IDR, AT91_RTC_ALARM);
+	at91_rtc_write_idr(AT91_RTC_ALARM);
 	at91_rtc_write(AT91_RTC_TIMALR,
 		  bin2bcd(tm.tm_sec) << 0
 		| bin2bcd(tm.tm_min) << 8
@@ -182,7 +238,7 @@ static int at91_rtc_setalarm(struct device *dev, struct rtc_wkalrm *alrm)
 
 	if (alrm->enabled) {
 		at91_rtc_write(AT91_RTC_SCCR, AT91_RTC_ALARM);
-		at91_rtc_write(AT91_RTC_IER, AT91_RTC_ALARM);
+		at91_rtc_write_ier(AT91_RTC_ALARM);
 	}
 
 	dev_dbg(dev, "%s(): %4d-%02d-%02d %02d:%02d:%02d\n", __func__,
@@ -198,9 +254,9 @@ static int at91_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 
 	if (enabled) {
 		at91_rtc_write(AT91_RTC_SCCR, AT91_RTC_ALARM);
-		at91_rtc_write(AT91_RTC_IER, AT91_RTC_ALARM);
+		at91_rtc_write_ier(AT91_RTC_ALARM);
 	} else
-		at91_rtc_write(AT91_RTC_IDR, AT91_RTC_ALARM);
+		at91_rtc_write_idr(AT91_RTC_ALARM);
 
 	return 0;
 }
@@ -209,7 +265,7 @@ static int at91_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
  */
 static int at91_rtc_proc(struct device *dev, struct seq_file *seq)
 {
-	unsigned long imr = at91_rtc_read(AT91_RTC_IMR);
+	unsigned long imr = at91_rtc_read_imr();
 
 	seq_printf(seq, "update_IRQ\t: %s\n",
 			(imr & AT91_RTC_ACKUPD) ? "yes" : "no");
@@ -229,7 +285,7 @@ static irqreturn_t at91_rtc_interrupt(int irq, void *dev_id)
 	unsigned int rtsr;
 	unsigned long events = 0;
 
-	rtsr = at91_rtc_read(AT91_RTC_SR) & at91_rtc_read(AT91_RTC_IMR);
+	rtsr = at91_rtc_read(AT91_RTC_SR) & at91_rtc_read_imr();
 	if (rtsr) {		/* this interrupt is shared!  Is it ours? */
 		if (rtsr & AT91_RTC_ALARM)
 			events |= (RTC_AF | RTC_IRQF);
@@ -250,6 +306,43 @@ static irqreturn_t at91_rtc_interrupt(int irq, void *dev_id)
 	return IRQ_NONE;		/* not handled */
 }
 
+static const struct at91_rtc_config at91rm9200_config = {
+};
+
+static const struct at91_rtc_config at91sam9x5_config = {
+	.use_shadow_imr	= true,
+};
+
+#ifdef CONFIG_OF
+static const struct of_device_id at91_rtc_dt_ids[] = {
+	{
+		.compatible = "atmel,at91rm9200-rtc",
+		.data = &at91rm9200_config,
+	}, {
+		.compatible = "atmel,at91sam9x5-rtc",
+		.data = &at91sam9x5_config,
+	}, {
+		/* sentinel */
+	}
+};
+MODULE_DEVICE_TABLE(of, at91_rtc_dt_ids);
+#endif
+
+static const struct at91_rtc_config *
+at91_rtc_get_config(struct platform_device *pdev)
+{
+	const struct of_device_id *match;
+
+	if (pdev->dev.of_node) {
+		match = of_match_node(at91_rtc_dt_ids, pdev->dev.of_node);
+		if (!match)
+			return NULL;
+		return (const struct at91_rtc_config *)match->data;
+	}
+
+	return &at91rm9200_config;
+}
+
 static const struct rtc_class_ops at91_rtc_ops = {
 	.read_time	= at91_rtc_readtime,
 	.set_time	= at91_rtc_settime,
@@ -268,6 +361,10 @@ static int __init at91_rtc_probe(struct platform_device *pdev)
 	struct resource *regs;
 	int ret = 0;
 
+	at91_rtc_config = at91_rtc_get_config(pdev);
+	if (!at91_rtc_config)
+		return -ENODEV;
+
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!regs) {
 		dev_err(&pdev->dev, "no mmio resource defined\n");
@@ -290,7 +387,7 @@ static int __init at91_rtc_probe(struct platform_device *pdev)
 	at91_rtc_write(AT91_RTC_MR, 0);		/* 24 hour mode */
 
 	/* Disable all interrupts */
-	at91_rtc_write(AT91_RTC_IDR, AT91_RTC_ACKUPD | AT91_RTC_ALARM |
+	at91_rtc_write_idr(AT91_RTC_ACKUPD | AT91_RTC_ALARM |
 					AT91_RTC_SECEV | AT91_RTC_TIMEV |
 					AT91_RTC_CALEV);
 
@@ -335,7 +432,7 @@ static int __exit at91_rtc_remove(struct platform_device *pdev)
 	struct rtc_device *rtc = platform_get_drvdata(pdev);
 
 	/* Disable all interrupts */
-	at91_rtc_write(AT91_RTC_IDR, AT91_RTC_ACKUPD | AT91_RTC_ALARM |
+	at91_rtc_write_idr(AT91_RTC_ACKUPD | AT91_RTC_ALARM |
 					AT91_RTC_SECEV | AT91_RTC_TIMEV |
 					AT91_RTC_CALEV);
 	free_irq(irq, pdev);
@@ -358,13 +455,13 @@ static int at91_rtc_suspend(struct device *dev)
 	/* this IRQ is shared with DBGU and other hardware which isn't
 	 * necessarily doing PM like we are...
 	 */
-	at91_rtc_imr = at91_rtc_read(AT91_RTC_IMR)
+	at91_rtc_imr = at91_rtc_read_imr()
 			& (AT91_RTC_ALARM|AT91_RTC_SECEV);
 	if (at91_rtc_imr) {
 		if (device_may_wakeup(dev))
 			enable_irq_wake(irq);
 		else
-			at91_rtc_write(AT91_RTC_IDR, at91_rtc_imr);
+			at91_rtc_write_idr(at91_rtc_imr);
 	}
 	return 0;
 }
@@ -375,7 +472,7 @@ static int at91_rtc_resume(struct device *dev)
 		if (device_may_wakeup(dev))
 			disable_irq_wake(irq);
 		else
-			at91_rtc_write(AT91_RTC_IER, at91_rtc_imr);
+			at91_rtc_write_ier(at91_rtc_imr);
 	}
 	return 0;
 }
@@ -383,12 +480,6 @@ static int at91_rtc_resume(struct device *dev)
 
 static SIMPLE_DEV_PM_OPS(at91_rtc_pm_ops, at91_rtc_suspend, at91_rtc_resume);
 
-static const struct of_device_id at91_rtc_dt_ids[] = {
-	{ .compatible = "atmel,at91rm9200-rtc" },
-	{ /* sentinel */ }
-};
-MODULE_DEVICE_TABLE(of, at91_rtc_dt_ids);
-
 static struct platform_driver at91_rtc_driver = {
 	.remove		= __exit_p(at91_rtc_remove),
 	.driver		= {
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index cc5bea9c4b1c..f1cb706445c7 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -854,6 +854,9 @@ static int cmos_resume(struct device *dev)
 		}
 
 		spin_lock_irq(&rtc_lock);
+		if (device_may_wakeup(dev))
+			hpet_rtc_timer_init();
+
 		do {
 			CMOS_WRITE(tmp, RTC_CONTROL);
 			hpet_set_rtc_irq_bit(tmp & RTC_IRQMASK);
@@ -869,7 +872,6 @@ static int cmos_resume(struct device *dev)
 			rtc_update_irq(cmos->rtc, 1, mask);
 			tmp &= ~RTC_AIE;
 			hpet_mask_rtc_irq_bit(RTC_AIE);
-			hpet_rtc_timer_init();
 		} while (mask & RTC_AIE);
 		spin_unlock_irq(&rtc_lock);
 	}
diff --git a/drivers/rtc/rtc-tps6586x.c b/drivers/rtc/rtc-tps6586x.c
index 459c2ffc95a6..426901cef14f 100644
--- a/drivers/rtc/rtc-tps6586x.c
+++ b/drivers/rtc/rtc-tps6586x.c
@@ -273,6 +273,8 @@ static int tps6586x_rtc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	device_init_wakeup(&pdev->dev, 1);
+
 	platform_set_drvdata(pdev, rtc);
 	rtc->rtc = devm_rtc_device_register(&pdev->dev, dev_name(&pdev->dev),
 				       &tps6586x_rtc_ops, THIS_MODULE);
@@ -292,7 +294,6 @@ static int tps6586x_rtc_probe(struct platform_device *pdev)
 		goto fail_rtc_register;
 	}
 	disable_irq(rtc->irq);
-	device_set_wakeup_capable(&pdev->dev, 1);
 	return 0;
 
 fail_rtc_register:
diff --git a/drivers/rtc/rtc-twl.c b/drivers/rtc/rtc-twl.c
index 8751a5240c99..b2eab34f38d9 100644
--- a/drivers/rtc/rtc-twl.c
+++ b/drivers/rtc/rtc-twl.c
@@ -524,6 +524,7 @@ static int twl_rtc_probe(struct platform_device *pdev)
 	}
 
 	platform_set_drvdata(pdev, rtc);
+	device_init_wakeup(&pdev->dev, 1);
 	return 0;
 
 out2:
diff --git a/fs/aio.c b/fs/aio.c
index 7fe5bdee1630..2bbcacf74d0c 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -141,9 +141,6 @@ static void aio_free_ring(struct kioctx *ctx)
 	for (i = 0; i < ctx->nr_pages; i++)
 		put_page(ctx->ring_pages[i]);
 
-	if (ctx->mmap_size)
-		vm_munmap(ctx->mmap_base, ctx->mmap_size);
-
 	if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages)
 		kfree(ctx->ring_pages);
 }
@@ -322,11 +319,6 @@ static void free_ioctx(struct kioctx *ctx)
 
 	aio_free_ring(ctx);
 
-	spin_lock(&aio_nr_lock);
-	BUG_ON(aio_nr - ctx->max_reqs > aio_nr);
-	aio_nr -= ctx->max_reqs;
-	spin_unlock(&aio_nr_lock);
-
 	pr_debug("freeing %p\n", ctx);
 
 	/*
@@ -435,17 +427,24 @@ static void kill_ioctx(struct kioctx *ctx)
 {
 	if (!atomic_xchg(&ctx->dead, 1)) {
 		hlist_del_rcu(&ctx->list);
-		/* Between hlist_del_rcu() and dropping the initial ref */
-		synchronize_rcu();
 
 		/*
-		 * We can't punt to workqueue here because put_ioctx() ->
-		 * free_ioctx() will unmap the ringbuffer, and that has to be
-		 * done in the original process's context. kill_ioctx_rcu/work()
-		 * exist for exit_aio(), as in that path free_ioctx() won't do
-		 * the unmap.
+		 * It'd be more correct to do this in free_ioctx(), after all
+		 * the outstanding kiocbs have finished - but by then io_destroy
+		 * has already returned, so io_setup() could potentially return
+		 * -EAGAIN with no ioctxs actually in use (as far as userspace
+		 *  could tell).
 		 */
-		kill_ioctx_work(&ctx->rcu_work);
+		spin_lock(&aio_nr_lock);
+		BUG_ON(aio_nr - ctx->max_reqs > aio_nr);
+		aio_nr -= ctx->max_reqs;
+		spin_unlock(&aio_nr_lock);
+
+		if (ctx->mmap_size)
+			vm_munmap(ctx->mmap_base, ctx->mmap_size);
+
+		/* Between hlist_del_rcu() and dropping the initial ref */
+		call_rcu(&ctx->rcu_head, kill_ioctx_rcu);
 	}
 }
 
@@ -495,10 +494,7 @@ void exit_aio(struct mm_struct *mm)
 		 */
 		ctx->mmap_size = 0;
 
-		if (!atomic_xchg(&ctx->dead, 1)) {
-			hlist_del_rcu(&ctx->list);
-			call_rcu(&ctx->rcu_head, kill_ioctx_rcu);
-		}
+		kill_ioctx(ctx);
 	}
 }
 
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index b3fdd1a323d6..e68588e6b1e8 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1408,6 +1408,7 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 				     mres->lockname_len, mres->lockname);
 				ret = -EFAULT;
 				spin_unlock(&res->spinlock);
+				dlm_lockres_put(res);
 				goto leave;
 			}
 			res->state |= DLM_LOCK_RES_MIGRATING;
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 04ee1b57c243..b4a5cdf9dbc5 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -947,7 +947,7 @@ leave:
 	ocfs2_free_dir_lookup_result(&orphan_insert);
 	ocfs2_free_dir_lookup_result(&lookup);
 
-	if (status)
+	if (status && (status != -ENOTEMPTY))
 		mlog_errno(status);
 
 	return status;
@@ -2216,7 +2216,7 @@ out:
 
 	brelse(orphan_dir_bh);
 
-	return 0;
+	return ret;
 }
 
 int ocfs2_create_inode_in_orphan(struct inode *dir,
diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c
index bd4b5a740ff1..bdfabdaefdce 100644
--- a/fs/proc/kmsg.c
+++ b/fs/proc/kmsg.c
@@ -21,12 +21,12 @@ extern wait_queue_head_t log_wait;
 
 static int kmsg_open(struct inode * inode, struct file * file)
 {
-	return do_syslog(SYSLOG_ACTION_OPEN, NULL, 0, SYSLOG_FROM_FILE);
+	return do_syslog(SYSLOG_ACTION_OPEN, NULL, 0, SYSLOG_FROM_PROC);
 }
 
 static int kmsg_release(struct inode * inode, struct file * file)
 {
-	(void) do_syslog(SYSLOG_ACTION_CLOSE, NULL, 0, SYSLOG_FROM_FILE);
+	(void) do_syslog(SYSLOG_ACTION_CLOSE, NULL, 0, SYSLOG_FROM_PROC);
 	return 0;
 }
 
@@ -34,15 +34,15 @@ static ssize_t kmsg_read(struct file *file, char __user *buf,
 			 size_t count, loff_t *ppos)
 {
 	if ((file->f_flags & O_NONBLOCK) &&
-	    !do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_FILE))
+	    !do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC))
 		return -EAGAIN;
-	return do_syslog(SYSLOG_ACTION_READ, buf, count, SYSLOG_FROM_FILE);
+	return do_syslog(SYSLOG_ACTION_READ, buf, count, SYSLOG_FROM_PROC);
 }
 
 static unsigned int kmsg_poll(struct file *file, poll_table *wait)
 {
 	poll_wait(file, &log_wait, wait);
-	if (do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_FILE))
+	if (do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC))
 		return POLLIN | POLLRDNORM;
 	return 0;
 }
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index c6f6e0839b61..9f3c7e81270a 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -175,6 +175,8 @@ extern struct bus_type cpu_subsys;
 
 extern void get_online_cpus(void);
 extern void put_online_cpus(void);
+extern void cpu_hotplug_disable(void);
+extern void cpu_hotplug_enable(void);
 #define hotcpu_notifier(fn, pri)	cpu_notifier(fn, pri)
 #define register_hotcpu_notifier(nb)	register_cpu_notifier(nb)
 #define unregister_hotcpu_notifier(nb)	unregister_cpu_notifier(nb)
@@ -198,6 +200,8 @@ static inline void cpu_hotplug_driver_unlock(void)
 
 #define get_online_cpus()	do { } while (0)
 #define put_online_cpus()	do { } while (0)
+#define cpu_hotplug_disable()	do { } while (0)
+#define cpu_hotplug_enable()	do { } while (0)
 #define hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
 /* These aren't inline functions due to a GCC bug. */
 #define register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
diff --git a/include/linux/math64.h b/include/linux/math64.h
index b8ba85544721..2913b86eb12a 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -6,7 +6,8 @@
 
 #if BITS_PER_LONG == 64
 
-#define div64_long(x,y) div64_s64((x),(y))
+#define div64_long(x, y) div64_s64((x), (y))
+#define div64_ul(x, y)   div64_u64((x), (y))
 
 /**
  * div_u64_rem - unsigned 64bit divide with 32bit divisor with remainder
@@ -47,7 +48,8 @@ static inline s64 div64_s64(s64 dividend, s64 divisor)
 
 #elif BITS_PER_LONG == 32
 
-#define div64_long(x,y) div_s64((x),(y))
+#define div64_long(x, y) div_s64((x), (y))
+#define div64_ul(x, y)   div_u64((x), (y))
 
 #ifndef div_u64_rem
 static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 47ead515c811..c5fd30d2a415 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -137,6 +137,7 @@ static inline void make_migration_entry_read(swp_entry_t *entry)
 
 extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					unsigned long address);
+extern void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte);
 #else
 
 #define make_migration_entry(page, write) swp_entry(0, 0)
@@ -148,6 +149,8 @@ static inline int is_migration_entry(swp_entry_t swp)
 static inline void make_migration_entry_read(swp_entry_t *entryp) { }
 static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					 unsigned long address) { }
+static inline void migration_entry_wait_huge(struct mm_struct *mm,
+					pte_t *pte) { }
 static inline int is_write_migration_entry(swp_entry_t entry)
 {
 	return 0;
diff --git a/include/linux/syslog.h b/include/linux/syslog.h
index 38911391a139..98a3153c0f96 100644
--- a/include/linux/syslog.h
+++ b/include/linux/syslog.h
@@ -44,8 +44,8 @@
 /* Return size of the log buffer */
 #define SYSLOG_ACTION_SIZE_BUFFER   10
 
-#define SYSLOG_FROM_CALL 0
-#define SYSLOG_FROM_FILE 1
+#define SYSLOG_FROM_READER           0
+#define SYSLOG_FROM_PROC             1
 
 int do_syslog(int type, char __user *buf, int count, bool from_file);
 
diff --git a/kernel/audit.c b/kernel/audit.c
index 21c7fa615bd3..91e53d04b6a9 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1056,7 +1056,7 @@ static inline void audit_get_stamp(struct audit_context *ctx,
 static void wait_for_auditd(unsigned long sleep_time)
 {
 	DECLARE_WAITQUEUE(wait, current);
-	set_current_state(TASK_INTERRUPTIBLE);
+	set_current_state(TASK_UNINTERRUPTIBLE);
 	add_wait_queue(&audit_backlog_wait, &wait);
 
 	if (audit_backlog_limit &&
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index a291aa23fb3f..43c307dc9453 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -658,6 +658,7 @@ int audit_add_tree_rule(struct audit_krule *rule)
 	struct vfsmount *mnt;
 	int err;
 
+	rule->tree = NULL;
 	list_for_each_entry(tree, &tree_list, list) {
 		if (!strcmp(seed->pathname, tree->pathname)) {
 			put_tree(seed);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index b5e4ab2d427e..198a38883e64 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -133,6 +133,27 @@ static void cpu_hotplug_done(void)
 	mutex_unlock(&cpu_hotplug.lock);
 }
 
+/*
+ * Wait for currently running CPU hotplug operations to complete (if any) and
+ * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects
+ * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the
+ * hotplug path before performing hotplug operations. So acquiring that lock
+ * guarantees mutual exclusion from any currently running hotplug operations.
+ */
+void cpu_hotplug_disable(void)
+{
+	cpu_maps_update_begin();
+	cpu_hotplug_disabled = 1;
+	cpu_maps_update_done();
+}
+
+void cpu_hotplug_enable(void)
+{
+	cpu_maps_update_begin();
+	cpu_hotplug_disabled = 0;
+	cpu_maps_update_done();
+}
+
 #else /* #if CONFIG_HOTPLUG_CPU */
 static void cpu_hotplug_begin(void) {}
 static void cpu_hotplug_done(void) {}
@@ -541,36 +562,6 @@ static int __init alloc_frozen_cpus(void)
 core_initcall(alloc_frozen_cpus);
 
 /*
- * Prevent regular CPU hotplug from racing with the freezer, by disabling CPU
- * hotplug when tasks are about to be frozen. Also, don't allow the freezer
- * to continue until any currently running CPU hotplug operation gets
- * completed.
- * To modify the 'cpu_hotplug_disabled' flag, we need to acquire the
- * 'cpu_add_remove_lock'. And this same lock is also taken by the regular
- * CPU hotplug path and released only after it is complete. Thus, we
- * (and hence the freezer) will block here until any currently running CPU
- * hotplug operation gets completed.
- */
-void cpu_hotplug_disable_before_freeze(void)
-{
-	cpu_maps_update_begin();
-	cpu_hotplug_disabled = 1;
-	cpu_maps_update_done();
-}
-
-
-/*
- * When tasks have been thawed, re-enable regular CPU hotplug (which had been
- * disabled while beginning to freeze tasks).
- */
-void cpu_hotplug_enable_after_thaw(void)
-{
-	cpu_maps_update_begin();
-	cpu_hotplug_disabled = 0;
-	cpu_maps_update_done();
-}
-
-/*
  * When callbacks for CPU hotplug notifications are being executed, we must
  * ensure that the state of the system with respect to the tasks being frozen
  * or not, as reported by the notification, remains unchanged *throughout the
@@ -589,12 +580,12 @@ cpu_hotplug_pm_callback(struct notifier_block *nb,
 
 	case PM_SUSPEND_PREPARE:
 	case PM_HIBERNATION_PREPARE:
-		cpu_hotplug_disable_before_freeze();
+		cpu_hotplug_disable();
 		break;
 
 	case PM_POST_SUSPEND:
 	case PM_POST_HIBERNATION:
-		cpu_hotplug_enable_after_thaw();
+		cpu_hotplug_enable();
 		break;
 
 	default:
diff --git a/kernel/printk.c b/kernel/printk.c
index fa36e1494420..8212c1aef125 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -363,6 +363,53 @@ static void log_store(int facility, int level,
 	log_next_seq++;
 }
 
+#ifdef CONFIG_SECURITY_DMESG_RESTRICT
+int dmesg_restrict = 1;
+#else
+int dmesg_restrict;
+#endif
+
+static int syslog_action_restricted(int type)
+{
+	if (dmesg_restrict)
+		return 1;
+	/*
+	 * Unless restricted, we allow "read all" and "get buffer size"
+	 * for everybody.
+	 */
+	return type != SYSLOG_ACTION_READ_ALL &&
+	       type != SYSLOG_ACTION_SIZE_BUFFER;
+}
+
+static int check_syslog_permissions(int type, bool from_file)
+{
+	/*
+	 * If this is from /proc/kmsg and we've already opened it, then we've
+	 * already done the capabilities checks at open time.
+	 */
+	if (from_file && type != SYSLOG_ACTION_OPEN)
+		return 0;
+
+	if (syslog_action_restricted(type)) {
+		if (capable(CAP_SYSLOG))
+			return 0;
+		/*
+		 * For historical reasons, accept CAP_SYS_ADMIN too, with
+		 * a warning.
+		 */
+		if (capable(CAP_SYS_ADMIN)) {
+			pr_warn_once("%s (%d): Attempt to access syslog with "
+				     "CAP_SYS_ADMIN but no CAP_SYSLOG "
+				     "(deprecated).\n",
+				 current->comm, task_pid_nr(current));
+			return 0;
+		}
+		return -EPERM;
+	}
+	return security_syslog(type);
+}
+
+
 /* /dev/kmsg - userspace message inject/listen interface */
 struct devkmsg_user {
 	u64 seq;
@@ -620,7 +667,8 @@ static int devkmsg_open(struct inode *inode, struct file *file)
 	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
 		return 0;
 
-	err = security_syslog(SYSLOG_ACTION_READ_ALL);
+	err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL,
+				       SYSLOG_FROM_READER);
 	if (err)
 		return err;
 
@@ -813,45 +861,6 @@ static inline void boot_delay_msec(int level)
 }
 #endif
 
-#ifdef CONFIG_SECURITY_DMESG_RESTRICT
-int dmesg_restrict = 1;
-#else
-int dmesg_restrict;
-#endif
-
-static int syslog_action_restricted(int type)
-{
-	if (dmesg_restrict)
-		return 1;
-	/* Unless restricted, we allow "read all" and "get buffer size" for everybody */
-	return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER;
-}
-
-static int check_syslog_permissions(int type, bool from_file)
-{
-	/*
-	 * If this is from /proc/kmsg and we've already opened it, then we've
-	 * already done the capabilities checks at open time.
-	 */
-	if (from_file && type != SYSLOG_ACTION_OPEN)
-		return 0;
-
-	if (syslog_action_restricted(type)) {
-		if (capable(CAP_SYSLOG))
-			return 0;
-		/* For historical reasons, accept CAP_SYS_ADMIN too, with a warning */
-		if (capable(CAP_SYS_ADMIN)) {
-			printk_once(KERN_WARNING "%s (%d): "
-				 "Attempt to access syslog with CAP_SYS_ADMIN "
-				 "but no CAP_SYSLOG (deprecated).\n",
-				 current->comm, task_pid_nr(current));
-			return 0;
-		}
-		return -EPERM;
-	}
-	return 0;
-}
-
 #if defined(CONFIG_PRINTK_TIME)
 static bool printk_time = 1;
 #else
@@ -1249,7 +1258,7 @@ out:
 
 SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len)
 {
-	return do_syslog(type, buf, len, SYSLOG_FROM_CALL);
+	return do_syslog(type, buf, len, SYSLOG_FROM_READER);
 }
 
 /*
diff --git a/kernel/sys.c b/kernel/sys.c
index b95d3c72ba21..2bbd9a73b54c 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -362,6 +362,29 @@ int unregister_reboot_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_reboot_notifier);
 
+/* Add backwards compatibility for stable trees. */
+#ifndef PF_NO_SETAFFINITY
+#define PF_NO_SETAFFINITY		PF_THREAD_BOUND
+#endif
+
+static void migrate_to_reboot_cpu(void)
+{
+	/* The boot cpu is always logical cpu 0 */
+	int cpu = 0;
+
+	cpu_hotplug_disable();
+
+	/* Make certain the cpu I'm about to reboot on is online */
+	if (!cpu_online(cpu))
+		cpu = cpumask_first(cpu_online_mask);
+
+	/* Prevent races with other tasks migrating this task */
+	current->flags |= PF_NO_SETAFFINITY;
+
+	/* Make certain I only run on the appropriate processor */
+	set_cpus_allowed_ptr(current, cpumask_of(cpu));
+}
+
 /**
  *	kernel_restart - reboot the system
  *	@cmd: pointer to buffer containing command to execute for restart
@@ -373,7 +396,7 @@ EXPORT_SYMBOL(unregister_reboot_notifier);
 void kernel_restart(char *cmd)
 {
 	kernel_restart_prepare(cmd);
-	disable_nonboot_cpus();
+	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	if (!cmd)
 		printk(KERN_EMERG "Restarting system.\n");
@@ -400,7 +423,7 @@ static void kernel_shutdown_prepare(enum system_states state)
 void kernel_halt(void)
 {
 	kernel_shutdown_prepare(SYSTEM_HALT);
-	disable_nonboot_cpus();
+	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	printk(KERN_EMERG "System halted.\n");
 	kmsg_dump(KMSG_DUMP_HALT);
@@ -419,7 +442,7 @@ void kernel_power_off(void)
 	kernel_shutdown_prepare(SYSTEM_POWER_OFF);
 	if (pm_power_off_prepare)
 		pm_power_off_prepare();
-	disable_nonboot_cpus();
+	migrate_to_reboot_cpu();
 	syscore_shutdown();
 	printk(KERN_EMERG "Power down.\n");
 	kmsg_dump(KMSG_DUMP_POWEROFF);
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index 5f9c44cdf1f5..4cc6442733f4 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -37,7 +37,7 @@ MPI mpi_read_raw_data(const void *xbuffer, size_t nbytes)
 	mpi_limb_t a;
 	MPI val = NULL;
 
-	while (nbytes >= 0 && buffer[0] == 0) {
+	while (nbytes > 0 && buffer[0] == 0) {
 		buffer++;
 		nbytes--;
 	}
diff --git a/mm/frontswap.c b/mm/frontswap.c
index 538367ef1372..1b24bdcb3197 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -319,7 +319,7 @@ void __frontswap_invalidate_area(unsigned type)
 			return;
 		frontswap_ops->invalidate_area(type);
 		atomic_set(&sis->frontswap_pages, 0);
-		memset(sis->frontswap_map, 0, sis->max / sizeof(long));
+		bitmap_zero(sis->frontswap_map, sis->max);
 	}
 	clear_bit(type, need_init);
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f8feeeca6686..e2bfbf73a551 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2839,7 +2839,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (ptep) {
 		entry = huge_ptep_get(ptep);
 		if (unlikely(is_hugetlb_entry_migration(entry))) {
-			migration_entry_wait(mm, (pmd_t *)ptep, address);
+			migration_entry_wait_huge(mm, ptep);
 			return 0;
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
 			return VM_FAULT_HWPOISON_LARGE |
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 010d6c14129a..194721839cf5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1199,7 +1199,6 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 
 			mz = mem_cgroup_zoneinfo(root, nid, zid);
 			iter = &mz->reclaim_iter[reclaim->priority];
-			last_visited = iter->last_visited;
 			if (prev && reclaim->generation != iter->generation) {
 				iter->last_visited = NULL;
 				goto out_unlock;
@@ -1218,13 +1217,12 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 			 * is alive.
 			 */
 			dead_count = atomic_read(&root->dead_count);
-			smp_rmb();
-			last_visited = iter->last_visited;
-			if (last_visited) {
-				if ((dead_count != iter->last_dead_count) ||
-					!css_tryget(&last_visited->css)) {
+			if (dead_count == iter->last_dead_count) {
+				smp_rmb();
+				last_visited = iter->last_visited;
+				if (last_visited &&
+				    !css_tryget(&last_visited->css))
 					last_visited = NULL;
-				}
 			}
 		}
 
@@ -3141,8 +3139,6 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups)
 			return -ENOMEM;
 		}
 
-		INIT_WORK(&s->memcg_params->destroy,
-				kmem_cache_destroy_work_func);
 		s->memcg_params->is_root_cache = true;
 
 		/*
diff --git a/mm/migrate.c b/mm/migrate.c
index b1f57501de9c..6f0c24438bba 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -200,15 +200,14 @@ static void remove_migration_ptes(struct page *old, struct page *new)
  * get to the page and wait until migration is finished.
  * When we return from this function the fault will be retried.
  */
-void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
-				unsigned long address)
+static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
+				spinlock_t *ptl)
 {
-	pte_t *ptep, pte;
-	spinlock_t *ptl;
+	pte_t pte;
 	swp_entry_t entry;
 	struct page *page;
 
-	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
+	spin_lock(ptl);
 	pte = *ptep;
 	if (!is_swap_pte(pte))
 		goto out;
@@ -236,6 +235,20 @@ out:
 	pte_unmap_unlock(ptep, ptl);
 }
 
+void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
+				unsigned long address)
+{
+	spinlock_t *ptl = pte_lockptr(mm, pmd);
+	pte_t *ptep = pte_offset_map(pmd, address);
+	__migration_entry_wait(mm, ptep, ptl);
+}
+
+void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte)
+{
+	spinlock_t *ptl = &(mm)->page_table_lock;
+	__migration_entry_wait(mm, pte, ptl);
+}
+
 #ifdef CONFIG_BLOCK
 /* Returns true if all buffers are successfully locked */
 static bool buffer_migrate_lock_buffers(struct buffer_head *head,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 378a15bcd649..c3edb624fccf 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1628,6 +1628,7 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 	long min = mark;
 	long lowmem_reserve = z->lowmem_reserve[classzone_idx];
 	int o;
+	long free_cma = 0;
 
 	free_pages -= (1 << order) - 1;
 	if (alloc_flags & ALLOC_HIGH)
@@ -1637,9 +1638,10 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 #ifdef CONFIG_CMA
 	/* If allocation can't use CMA areas don't use free CMA pages */
 	if (!(alloc_flags & ALLOC_CMA))
-		free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
+		free_cma = zone_page_state(z, NR_FREE_CMA_PAGES);
 #endif
-	if (free_pages <= min + lowmem_reserve)
+
+	if (free_pages - free_cma <= min + lowmem_reserve)
 		return false;
 	for (o = 0; o < order; o++) {
 		/* At the next order, this order's pages become unavailable */
diff --git a/mm/swap_state.c b/mm/swap_state.c
index b3d40dcf3624..f24ab0dff554 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -336,8 +336,24 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * Swap entry may have been freed since our caller observed it.
 		 */
 		err = swapcache_prepare(entry);
-		if (err == -EEXIST) {	/* seems racy */
+		if (err == -EEXIST) {
 			radix_tree_preload_end();
+			/*
+			 * We might race against get_swap_page() and stumble
+			 * across a SWAP_HAS_CACHE swap_map entry whose page
+			 * has not been brought into the swapcache yet, while
+			 * the other end is scheduled away waiting on discard
+			 * I/O completion at scan_swap_map().
+			 *
+			 * In order to avoid turning this transitory state
+			 * into a permanent loop around this -EEXIST case
+			 * if !CONFIG_PREEMPT and the I/O completion happens
+			 * to be waiting on the CPU waitqueue where we are now
+			 * busy looping, we just conditionally invoke the
+			 * scheduler here, if there are some more important
+			 * tasks to run.
+			 */
+			cond_resched();
 			continue;
 		}
 		if (err) {		/* swp entry is obsolete ? */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 6c340d908b27..746af55b8455 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2116,7 +2116,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	}
 	/* frontswap enabled? set up bit-per-page map for frontswap */
 	if (frontswap_enabled)
-		frontswap_map = vzalloc(maxpages / sizeof(long));
+		frontswap_map = vzalloc(BITS_TO_LONGS(maxpages) * sizeof(long));
 
 	if (p->bdev) {
 		if (blk_queue_nonrot(bdev_get_queue(p->bdev))) {