16 files changed, 258 insertions, 110 deletions

diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt
index ead764b2728..de1e6c4dccf 100644
--- a/Documentation/filesystems/vfat.txt
+++ b/Documentation/filesystems/vfat.txt
@@ -137,6 +137,17 @@ errors=panic|continue|remount-ro
 		 without doing anything or remount the partition in
 		 read-only mode (default behavior).
 
+discard       -- If set, issues discard/TRIM commands to the block
+		 device when blocks are freed. This is useful for SSD devices
+		 and sparse/thinly-provisoned LUNs.
+
+nfs           -- This option maintains an index (cache) of directory
+		 inodes by i_logstart which is used by the nfs-related code to
+		 improve look-ups.
+
+		 Enable this only if you want to export the FAT filesystem
+		 over NFS
+
 <bool>: 0,1,yes,no,true,false
 
 TODO
diff --git a/Documentation/vm/hugetlbpage.txt b/Documentation/vm/hugetlbpage.txt
index f8551b3879f..4ac359b7aa1 100644
--- a/Documentation/vm/hugetlbpage.txt
+++ b/Documentation/vm/hugetlbpage.txt
@@ -299,11 +299,17 @@ map_hugetlb.c.
 *******************************************************************
 
 /*
- * hugepage-shm:  see Documentation/vm/hugepage-shm.c
+ * map_hugetlb: see tools/testing/selftests/vm/map_hugetlb.c
  */
 
 *******************************************************************
 
 /*
- * hugepage-mmap:  see Documentation/vm/hugepage-mmap.c
+ * hugepage-shm:  see tools/testing/selftests/vm/hugepage-shm.c
+ */
+
+*******************************************************************
+
+/*
+ * hugepage-mmap:  see tools/testing/selftests/vm/hugepage-mmap.c
  */
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index f6679a7fb8c..b91e4851242 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -56,9 +56,16 @@ static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
 }
 
 /*
- * search for a shareable pmd page for hugetlb.
+ * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
+ * and returns the corresponding pte. While this is not necessary for the
+ * !shared pmd case because we can allocate the pmd later as well, it makes the
+ * code much cleaner. pmd allocation is essential for the shared case because
+ * pud has to be populated inside the same i_mmap_mutex section - otherwise
+ * racing tasks could either miss the sharing (see huge_pte_offset) or select a
+ * bad pmd for sharing.
  */
-static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+static pte_t *
+huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 {
 	struct vm_area_struct *vma = find_vma(mm, addr);
 	struct address_space *mapping = vma->vm_file->f_mapping;
@@ -68,9 +75,10 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	struct vm_area_struct *svma;
 	unsigned long saddr;
 	pte_t *spte = NULL;
+	pte_t *pte;
 
 	if (!vma_shareable(vma, addr))
-		return;
+		return (pte_t *)pmd_alloc(mm, pud, addr);
 
 	mutex_lock(&mapping->i_mmap_mutex);
 	vma_prio_tree_foreach(svma, &iter, &mapping->i_mmap, idx, idx) {
@@ -97,7 +105,9 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 		put_page(virt_to_page(spte));
 	spin_unlock(&mm->page_table_lock);
 out:
+	pte = (pte_t *)pmd_alloc(mm, pud, addr);
 	mutex_unlock(&mapping->i_mmap_mutex);
+	return pte;
 }
 
 /*
@@ -142,8 +152,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		} else {
 			BUG_ON(sz != PMD_SIZE);
 			if (pud_none(*pud))
-				huge_pmd_share(mm, addr, pud);
-			pte = (pte_t *) pmd_alloc(mm, pud, addr);
+				pte = huge_pmd_share(mm, addr, pud);
+			else
+				pte = (pte_t *)pmd_alloc(mm, pud, addr);
 		}
 	}
 	BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
diff --git a/drivers/block/cciss_scsi.c b/drivers/block/cciss_scsi.c
index acda773b372..38aa6dda6b8 100644
--- a/drivers/block/cciss_scsi.c
+++ b/drivers/block/cciss_scsi.c
@@ -763,16 +763,7 @@ static void complete_scsi_command(CommandList_struct *c, int timeout,
 		{
 			case CMD_TARGET_STATUS:
 				/* Pass it up to the upper layers... */
-				if( ei->ScsiStatus)
-                		{
-#if 0
-                    			printk(KERN_WARNING "cciss: cmd %p "
-						"has SCSI Status = %x\n",
-						c, ei->ScsiStatus);
-#endif
-					cmd->result |= (ei->ScsiStatus << 1);
-                		}
-				else {  /* scsi status is zero??? How??? */
+				if (!ei->ScsiStatus) {
 					
 	/* Ordinarily, this case should never happen, but there is a bug
 	   in some released firmware revisions that allows it to happen
diff --git a/drivers/clocksource/cs5535-clockevt.c b/drivers/clocksource/cs5535-clockevt.c
index 540795cd076..d9279385304 100644
--- a/drivers/clocksource/cs5535-clockevt.c
+++ b/drivers/clocksource/cs5535-clockevt.c
@@ -53,7 +53,7 @@ static struct cs5535_mfgpt_timer *cs5535_event_clock;
 #define MFGPT_PERIODIC (MFGPT_HZ / HZ)
 
 /*
- * The MFPGT timers on the CS5536 provide us with suitable timers to use
+ * The MFGPT timers on the CS5536 provide us with suitable timers to use
  * as clock event sources - not as good as a HPET or APIC, but certainly
  * better than the PIT.  This isn't a general purpose MFGPT driver, but
  * a simplified one designed specifically to act as a clock event source.
@@ -144,7 +144,7 @@ static int __init cs5535_mfgpt_init(void)
 
 	timer = cs5535_mfgpt_alloc_timer(MFGPT_TIMER_ANY, MFGPT_DOMAIN_WORKING);
 	if (!timer) {
-		printk(KERN_ERR DRV_NAME ": Could not allocate MFPGT timer\n");
+		printk(KERN_ERR DRV_NAME ": Could not allocate MFGPT timer\n");
 		return -ENODEV;
 	}
 	cs5535_event_clock = timer;
diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c
index 87b251ab6ec..b9e2000969f 100644
--- a/drivers/misc/sgi-xp/xpc_uv.c
+++ b/drivers/misc/sgi-xp/xpc_uv.c
@@ -18,6 +18,8 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/device.h>
+#include <linux/cpu.h>
+#include <linux/module.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <asm/uv/uv_hub.h>
@@ -59,6 +61,8 @@ static struct xpc_heartbeat_uv *xpc_heartbeat_uv;
 					 XPC_NOTIFY_MSG_SIZE_UV)
 #define XPC_NOTIFY_IRQ_NAME		"xpc_notify"
 
+static int xpc_mq_node = -1;
+
 static struct xpc_gru_mq_uv *xpc_activate_mq_uv;
 static struct xpc_gru_mq_uv *xpc_notify_mq_uv;
 
@@ -109,11 +113,8 @@ xpc_get_gru_mq_irq_uv(struct xpc_gru_mq_uv *mq, int cpu, char *irq_name)
 #if defined CONFIG_X86_64
 	mq->irq = uv_setup_irq(irq_name, cpu, mq->mmr_blade, mq->mmr_offset,
 			UV_AFFINITY_CPU);
-	if (mq->irq < 0) {
-		dev_err(xpc_part, "uv_setup_irq() returned error=%d\n",
-			-mq->irq);
+	if (mq->irq < 0)
 		return mq->irq;
-	}
 
 	mq->mmr_value = uv_read_global_mmr64(mmr_pnode, mq->mmr_offset);
 
@@ -238,8 +239,9 @@ xpc_create_gru_mq_uv(unsigned int mq_size, int cpu, char *irq_name,
 	mq->mmr_blade = uv_cpu_to_blade_id(cpu);
 
 	nid = cpu_to_node(cpu);
-	page = alloc_pages_exact_node(nid, GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
-				pg_order);
+	page = alloc_pages_exact_node(nid,
+				      GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+				      pg_order);
 	if (page == NULL) {
 		dev_err(xpc_part, "xpc_create_gru_mq_uv() failed to alloc %d "
 			"bytes of memory on nid=%d for GRU mq\n", mq_size, nid);
@@ -1731,9 +1733,50 @@ static struct xpc_arch_operations xpc_arch_ops_uv = {
 	.notify_senders_of_disconnect = xpc_notify_senders_of_disconnect_uv,
 };
 
+static int
+xpc_init_mq_node(int nid)
+{
+	int cpu;
+
+	get_online_cpus();
+
+	for_each_cpu(cpu, cpumask_of_node(nid)) {
+		xpc_activate_mq_uv =
+			xpc_create_gru_mq_uv(XPC_ACTIVATE_MQ_SIZE_UV, nid,
+					     XPC_ACTIVATE_IRQ_NAME,
+					     xpc_handle_activate_IRQ_uv);
+		if (!IS_ERR(xpc_activate_mq_uv))
+			break;
+	}
+	if (IS_ERR(xpc_activate_mq_uv)) {
+		put_online_cpus();
+		return PTR_ERR(xpc_activate_mq_uv);
+	}
+
+	for_each_cpu(cpu, cpumask_of_node(nid)) {
+		xpc_notify_mq_uv =
+			xpc_create_gru_mq_uv(XPC_NOTIFY_MQ_SIZE_UV, nid,
+					     XPC_NOTIFY_IRQ_NAME,
+					     xpc_handle_notify_IRQ_uv);
+		if (!IS_ERR(xpc_notify_mq_uv))
+			break;
+	}
+	if (IS_ERR(xpc_notify_mq_uv)) {
+		xpc_destroy_gru_mq_uv(xpc_activate_mq_uv);
+		put_online_cpus();
+		return PTR_ERR(xpc_notify_mq_uv);
+	}
+
+	put_online_cpus();
+	return 0;
+}
+
 int
 xpc_init_uv(void)
 {
+	int nid;
+	int ret = 0;
+
 	xpc_arch_ops = xpc_arch_ops_uv;
 
 	if (sizeof(struct xpc_notify_mq_msghdr_uv) > XPC_MSG_HDR_MAX_SIZE) {
@@ -1742,21 +1785,21 @@ xpc_init_uv(void)
 		return -E2BIG;
 	}
 
-	xpc_activate_mq_uv = xpc_create_gru_mq_uv(XPC_ACTIVATE_MQ_SIZE_UV, 0,
-						  XPC_ACTIVATE_IRQ_NAME,
-						  xpc_handle_activate_IRQ_uv);
-	if (IS_ERR(xpc_activate_mq_uv))
-		return PTR_ERR(xpc_activate_mq_uv);
+	if (xpc_mq_node < 0)
+		for_each_online_node(nid) {
+			ret = xpc_init_mq_node(nid);
 
-	xpc_notify_mq_uv = xpc_create_gru_mq_uv(XPC_NOTIFY_MQ_SIZE_UV, 0,
-						XPC_NOTIFY_IRQ_NAME,
-						xpc_handle_notify_IRQ_uv);
-	if (IS_ERR(xpc_notify_mq_uv)) {
-		xpc_destroy_gru_mq_uv(xpc_activate_mq_uv);
-		return PTR_ERR(xpc_notify_mq_uv);
-	}
+			if (!ret)
+				break;
+		}
+	else
+		ret = xpc_init_mq_node(xpc_mq_node);
 
-	return 0;
+	if (ret < 0)
+		dev_err(xpc_part, "xpc_init_mq_node() returned error=%d\n",
+			-ret);
+
+	return ret;
 }
 
 void
@@ -1765,3 +1808,6 @@ xpc_exit_uv(void)
 	xpc_destroy_gru_mq_uv(xpc_notify_mq_uv);
 	xpc_destroy_gru_mq_uv(xpc_activate_mq_uv);
 }
+
+module_param(xpc_mq_node, int, 0);
+MODULE_PARM_DESC(xpc_mq_node, "Node number on which to allocate message queues.");
diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c
index 722246cf20a..5d44252b734 100644
--- a/drivers/rapidio/devices/tsi721.c
+++ b/drivers/rapidio/devices/tsi721.c
@@ -435,6 +435,9 @@ static void tsi721_db_dpc(struct work_struct *work)
 				" info %4.4x\n", DBELL_SID(idb.bytes),
 				DBELL_TID(idb.bytes), DBELL_INF(idb.bytes));
 		}
+
+		wr_ptr = ioread32(priv->regs +
+				  TSI721_IDQ_WP(IDB_QUEUE)) % IDB_QSIZE;
 	}
 
 	iowrite32(rd_ptr & (IDB_QSIZE - 1),
@@ -445,6 +448,10 @@ static void tsi721_db_dpc(struct work_struct *work)
 	regval |= TSI721_SR_CHINT_IDBQRCV;
 	iowrite32(regval,
 		priv->regs + TSI721_SR_CHINTE(IDB_QUEUE));
+
+	wr_ptr = ioread32(priv->regs + TSI721_IDQ_WP(IDB_QUEUE)) % IDB_QSIZE;
+	if (wr_ptr != rd_ptr)
+		schedule_work(&priv->idb_work);
 }
 
 /**
@@ -2212,7 +2219,7 @@ static int __devinit tsi721_probe(struct pci_dev *pdev,
 				  const struct pci_device_id *id)
 {
 	struct tsi721_device *priv;
-	int i, cap;
+	int cap;
 	int err;
 	u32 regval;
 
@@ -2232,12 +2239,15 @@ static int __devinit tsi721_probe(struct pci_dev *pdev,
 	priv->pdev = pdev;
 
 #ifdef DEBUG
+	{
+	int i;
 	for (i = 0; i <= PCI_STD_RESOURCE_END; i++) {
 		dev_dbg(&pdev->dev, "res[%d] @ 0x%llx (0x%lx, 0x%lx)\n",
 			i, (unsigned long long)pci_resource_start(pdev, i),
 			(unsigned long)pci_resource_len(pdev, i),
 			pci_resource_flags(pdev, i));
 	}
+	}
 #endif
 	/*
 	 * Verify BAR configuration
diff --git a/drivers/rtc/rtc-pcf2123.c b/drivers/rtc/rtc-pcf2123.c
index 836118795c0..13e4df63974 100644
--- a/drivers/rtc/rtc-pcf2123.c
+++ b/drivers/rtc/rtc-pcf2123.c
@@ -43,6 +43,7 @@
 #include <linux/rtc.h>
 #include <linux/spi/spi.h>
 #include <linux/module.h>
+#include <linux/sysfs.h>
 
 #define DRV_VERSION "0.6"
 
@@ -292,6 +293,7 @@ static int __devinit pcf2123_probe(struct spi_device *spi)
 	pdata->rtc = rtc;
 
 	for (i = 0; i < 16; i++) {
+		sysfs_attr_init(&pdata->regs[i].attr.attr);
 		sprintf(pdata->regs[i].name, "%1x", i);
 		pdata->regs[i].attr.attr.mode = S_IRUGO | S_IWUSR;
 		pdata->regs[i].attr.attr.name = pdata->regs[i].name;
diff --git a/drivers/rtc/rtc-rs5c348.c b/drivers/rtc/rtc-rs5c348.c
index 77074ccd285..fd5c7af04ae 100644
--- a/drivers/rtc/rtc-rs5c348.c
+++ b/drivers/rtc/rtc-rs5c348.c
@@ -122,9 +122,12 @@ rs5c348_rtc_read_time(struct device *dev, struct rtc_time *tm)
 	tm->tm_min = bcd2bin(rxbuf[RS5C348_REG_MINS] & RS5C348_MINS_MASK);
 	tm->tm_hour = bcd2bin(rxbuf[RS5C348_REG_HOURS] & RS5C348_HOURS_MASK);
 	if (!pdata->rtc_24h) {
-		tm->tm_hour %= 12;
-		if (rxbuf[RS5C348_REG_HOURS] & RS5C348_BIT_PM)
+		if (rxbuf[RS5C348_REG_HOURS] & RS5C348_BIT_PM) {
+			tm->tm_hour -= 20;
+			tm->tm_hour %= 12;
 			tm->tm_hour += 12;
+		} else
+			tm->tm_hour %= 12;
 	}
 	tm->tm_wday = bcd2bin(rxbuf[RS5C348_REG_WDAY] & RS5C348_WDAY_MASK);
 	tm->tm_mday = bcd2bin(rxbuf[RS5C348_REG_DAY] & RS5C348_DAY_MASK);
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 133ddcf8339..ef658147e4e 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -22,7 +22,7 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
-			bool sync);
+			bool sync, bool *contended);
 extern int compact_pgdat(pg_data_t *pgdat, int order);
 extern unsigned long compaction_suitable(struct zone *zone, int order);
 
@@ -64,7 +64,7 @@ static inline bool compaction_deferred(struct zone *zone, int order)
 #else
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			bool sync)
+			bool sync, bool *contended)
 {
 	return COMPACT_CONTINUE;
 }
diff --git a/include/linux/string.h b/include/linux/string.h
index ffe0442e18d..b9178812d9d 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -144,8 +144,8 @@ static inline bool strstarts(const char *str, const char *prefix)
 {
 	return strncmp(str, prefix, strlen(prefix)) == 0;
 }
-#endif
 
 extern size_t memweight(const void *ptr, size_t bytes);
 
+#endif /* __KERNEL__ */
 #endif /* _LINUX_STRING_H_ */
diff --git a/mm/compaction.c b/mm/compaction.c
index e78cb968842..7fcd3a52e68 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -51,6 +51,47 @@ static inline bool migrate_async_suitable(int migratetype)
 }
 
 /*
+ * Compaction requires the taking of some coarse locks that are potentially
+ * very heavily contended. Check if the process needs to be scheduled or
+ * if the lock is contended. For async compaction, back out in the event
+ * if contention is severe. For sync compaction, schedule.
+ *
+ * Returns true if the lock is held.
+ * Returns false if the lock is released and compaction should abort
+ */
+static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,
+				      bool locked, struct compact_control *cc)
+{
+	if (need_resched() || spin_is_contended(lock)) {
+		if (locked) {
+			spin_unlock_irqrestore(lock, *flags);
+			locked = false;
+		}
+
+		/* async aborts if taking too long or contended */
+		if (!cc->sync) {
+			if (cc->contended)
+				*cc->contended = true;
+			return false;
+		}
+
+		cond_resched();
+		if (fatal_signal_pending(current))
+			return false;
+	}
+
+	if (!locked)
+		spin_lock_irqsave(lock, *flags);
+	return true;
+}
+
+static inline bool compact_trylock_irqsave(spinlock_t *lock,
+			unsigned long *flags, struct compact_control *cc)
+{
+	return compact_checklock_irqsave(lock, flags, false, cc);
+}
+
+/*
  * Isolate free pages onto a private freelist. Caller must hold zone->lock.
  * If @strict is true, will abort returning 0 on any invalid PFNs or non-free
  * pages inside of the pageblock (even though it may still end up isolating
@@ -173,7 +214,7 @@ isolate_freepages_range(unsigned long start_pfn, unsigned long end_pfn)
 }
 
 /* Update the number of anon and file isolated pages in the zone */
-static void acct_isolated(struct zone *zone, struct compact_control *cc)
+static void acct_isolated(struct zone *zone, bool locked, struct compact_control *cc)
 {
 	struct page *page;
 	unsigned int count[2] = { 0, };
@@ -181,8 +222,14 @@ static void acct_isolated(struct zone *zone, struct compact_control *cc)
 	list_for_each_entry(page, &cc->migratepages, lru)
 		count[!!page_is_file_cache(page)]++;
 
-	__mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
-	__mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
+	/* If locked we can use the interrupt unsafe versions */
+	if (locked) {
+		__mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
+		__mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
+	} else {
+		mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
+		mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
+	}
 }
 
 /* Similar to reclaim, but different enough that they don't share logic */
@@ -228,6 +275,8 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	struct list_head *migratelist = &cc->migratepages;
 	isolate_mode_t mode = 0;
 	struct lruvec *lruvec;
+	unsigned long flags;
+	bool locked;
 
 	/*
 	 * Ensure that there are not too many pages isolated from the LRU
@@ -247,25 +296,22 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 
 	/* Time to isolate some pages for migration */
 	cond_resched();
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irqsave(&zone->lru_lock, flags);
+	locked = true;
 	for (; low_pfn < end_pfn; low_pfn++) {
 		struct page *page;
-		bool locked = true;
 
 		/* give a chance to irqs before checking need_resched() */
 		if (!((low_pfn+1) % SWAP_CLUSTER_MAX)) {
-			spin_unlock_irq(&zone->lru_lock);
+			spin_unlock_irqrestore(&zone->lru_lock, flags);
 			locked = false;
 		}
-		if (need_resched() || spin_is_contended(&zone->lru_lock)) {
-			if (locked)
-				spin_unlock_irq(&zone->lru_lock);
-			cond_resched();
-			spin_lock_irq(&zone->lru_lock);
-			if (fatal_signal_pending(current))
-				break;
-		} else if (!locked)
-			spin_lock_irq(&zone->lru_lock);
+
+		/* Check if it is ok to still hold the lock */
+		locked = compact_checklock_irqsave(&zone->lru_lock, &flags,
+								locked, cc);
+		if (!locked)
+			break;
 
 		/*
 		 * migrate_pfn does not necessarily start aligned to a
@@ -349,9 +395,10 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 		}
 	}
 
-	acct_isolated(zone, cc);
+	acct_isolated(zone, locked, cc);
 
-	spin_unlock_irq(&zone->lru_lock);
+	if (locked)
+		spin_unlock_irqrestore(&zone->lru_lock, flags);
 
 	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
 
@@ -384,6 +431,20 @@ static bool suitable_migration_target(struct page *page)
 }
 
 /*
+ * Returns the start pfn of the last page block in a zone.  This is the starting
+ * point for full compaction of a zone.  Compaction searches for free pages from
+ * the end of each zone, while isolate_freepages_block scans forward inside each
+ * page block.
+ */
+static unsigned long start_free_pfn(struct zone *zone)
+{
+	unsigned long free_pfn;
+	free_pfn = zone->zone_start_pfn + zone->spanned_pages;
+	free_pfn &= ~(pageblock_nr_pages-1);
+	return free_pfn;
+}
+
+/*
  * Based on information in the current compact_control, find blocks
  * suitable for isolating free pages from and then isolate them.
  */
@@ -422,17 +483,6 @@ static void isolate_freepages(struct zone *zone,
 					pfn -= pageblock_nr_pages) {
 		unsigned long isolated;
 
-		/*
-		 * Skip ahead if another thread is compacting in the area
-		 * simultaneously. If we wrapped around, we can only skip
-		 * ahead if zone->compact_cached_free_pfn also wrapped to
-		 * above our starting point.
-		 */
-		if (cc->order > 0 && (!cc->wrapped ||
-				      zone->compact_cached_free_pfn >
-				      cc->start_free_pfn))
-			pfn = min(pfn, zone->compact_cached_free_pfn);
-
 		if (!pfn_valid(pfn))
 			continue;
 
@@ -458,7 +508,16 @@ static void isolate_freepages(struct zone *zone,
 		 * are disabled
 		 */
 		isolated = 0;
-		spin_lock_irqsave(&zone->lock, flags);
+
+		/*
+		 * The zone lock must be held to isolate freepages. This
+		 * unfortunately this is a very coarse lock and can be
+		 * heavily contended if there are parallel allocations
+		 * or parallel compactions. For async compaction do not
+		 * spin on the lock
+		 */
+		if (!compact_trylock_irqsave(&zone->lock, &flags, cc))
+			break;
 		if (suitable_migration_target(page)) {
 			end_pfn = min(pfn + pageblock_nr_pages, zone_end_pfn);
 			isolated = isolate_freepages_block(pfn, end_pfn,
@@ -474,7 +533,15 @@ static void isolate_freepages(struct zone *zone,
 		 */
 		if (isolated) {
 			high_pfn = max(high_pfn, pfn);
-			if (cc->order > 0)
+
+			/*
+			 * If the free scanner has wrapped, update
+			 * compact_cached_free_pfn to point to the highest
+			 * pageblock with free pages. This reduces excessive
+			 * scanning of full pageblocks near the end of the
+			 * zone
+			 */
+			if (cc->order > 0 && cc->wrapped)
 				zone->compact_cached_free_pfn = high_pfn;
 		}
 	}
@@ -484,6 +551,11 @@ static void isolate_freepages(struct zone *zone,
 
 	cc->free_pfn = high_pfn;
 	cc->nr_freepages = nr_freepages;
+
+	/* If compact_cached_free_pfn is reset then set it now */
+	if (cc->order > 0 && !cc->wrapped &&
+			zone->compact_cached_free_pfn == start_free_pfn(zone))
+		zone->compact_cached_free_pfn = high_pfn;
 }
 
 /*
@@ -570,20 +642,6 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	return ISOLATE_SUCCESS;
 }
 
-/*
- * Returns the start pfn of the last page block in a zone.  This is the starting
- * point for full compaction of a zone.  Compaction searches for free pages from
- * the end of each zone, while isolate_freepages_block scans forward inside each
- * page block.
- */
-static unsigned long start_free_pfn(struct zone *zone)
-{
-	unsigned long free_pfn;
-	free_pfn = zone->zone_start_pfn + zone->spanned_pages;
-	free_pfn &= ~(pageblock_nr_pages-1);
-	return free_pfn;
-}
-
 static int compact_finished(struct zone *zone,
 			    struct compact_control *cc)
 {
@@ -771,7 +829,7 @@ out:
 
 static unsigned long compact_zone_order(struct zone *zone,
 				 int order, gfp_t gfp_mask,
-				 bool sync)
+				 bool sync, bool *contended)
 {
 	struct compact_control cc = {
 		.nr_freepages = 0,
@@ -780,6 +838,7 @@ static unsigned long compact_zone_order(struct zone *zone,
 		.migratetype = allocflags_to_migratetype(gfp_mask),
 		.zone = zone,
 		.sync = sync,
+		.contended = contended,
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -801,7 +860,7 @@ int sysctl_extfrag_threshold = 500;
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			bool sync)
+			bool sync, bool *contended)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
@@ -825,7 +884,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 								nodemask) {
 		int status;
 
-		status = compact_zone_order(zone, order, gfp_mask, sync);
+		status = compact_zone_order(zone, order, gfp_mask, sync,
+						contended);
 		rc = max(status, rc);
 
 		/* If a normal allocation would succeed, stop compacting */
@@ -861,7 +921,7 @@ static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
 		if (cc->order > 0) {
 			int ok = zone_watermark_ok(zone, cc->order,
 						low_wmark_pages(zone), 0, 0);
-			if (ok && cc->order > zone->compact_order_failed)
+			if (ok && cc->order >= zone->compact_order_failed)
 				zone->compact_order_failed = cc->order + 1;
 			/* Currently async compaction is never deferred. */
 			else if (!ok && cc->sync)
diff --git a/mm/internal.h b/mm/internal.h
index 3314f79d775..b8c91b342e2 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -130,6 +130,7 @@ struct compact_control {
 	int order;			/* order a direct compactor needs */
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
 	struct zone *zone;
+	bool *contended;		/* True if a lock was contended */
 };
 
 unsigned long
diff --git a/mm/mmap.c b/mm/mmap.c
index e3e86914f11..9adee9fc0d8 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2309,7 +2309,7 @@ void exit_mmap(struct mm_struct *mm)
 	}
 	vm_unacct_memory(nr_accounted);
 
-	BUG_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
+	WARN_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
 }
 
 /* Insert vm structure into process list sorted by address
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 009ac285fea..c66fb875104 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1928,6 +1928,17 @@ this_zone_full:
 		zlc_active = 0;
 		goto zonelist_scan;
 	}
+
+	if (page)
+		/*
+		 * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was
+		 * necessary to allocate the page. The expectation is
+		 * that the caller is taking steps that will free more
+		 * memory. The caller should avoid the page being used
+		 * for !PFMEMALLOC purposes.
+		 */
+		page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS);
+
 	return page;
 }
 
@@ -2091,7 +2102,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
 	int migratetype, bool sync_migration,
-	bool *deferred_compaction,
+	bool *contended_compaction, bool *deferred_compaction,
 	unsigned long *did_some_progress)
 {
 	struct page *page;
@@ -2106,7 +2117,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 
 	current->flags |= PF_MEMALLOC;
 	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
-						nodemask, sync_migration);
+						nodemask, sync_migration,
+						contended_compaction);
 	current->flags &= ~PF_MEMALLOC;
 	if (*did_some_progress != COMPACT_SKIPPED) {
 
@@ -2152,7 +2164,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
 	int migratetype, bool sync_migration,
-	bool *deferred_compaction,
+	bool *contended_compaction, bool *deferred_compaction,
 	unsigned long *did_some_progress)
 {
 	return NULL;
@@ -2325,6 +2337,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	unsigned long did_some_progress;
 	bool sync_migration = false;
 	bool deferred_compaction = false;
+	bool contended_compaction = false;
 
 	/*
 	 * In the slowpath, we sanity check order to avoid ever trying to
@@ -2389,14 +2402,6 @@ rebalance:
 				zonelist, high_zoneidx, nodemask,
 				preferred_zone, migratetype);
 		if (page) {
-			/*
-			 * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was
-			 * necessary to allocate the page. The expectation is
-			 * that the caller is taking steps that will free more
-			 * memory. The caller should avoid the page being used
-			 * for !PFMEMALLOC purposes.
-			 */
-			page->pfmemalloc = true;
 			goto got_pg;
 		}
 	}
@@ -2422,6 +2427,7 @@ rebalance:
 					nodemask,
 					alloc_flags, preferred_zone,
 					migratetype, sync_migration,
+					&contended_compaction,
 					&deferred_compaction,
 					&did_some_progress);
 	if (page)
@@ -2431,10 +2437,11 @@ rebalance:
 	/*
 	 * If compaction is deferred for high-order allocations, it is because
 	 * sync compaction recently failed. In this is the case and the caller
-	 * has requested the system not be heavily disrupted, fail the
-	 * allocation now instead of entering direct reclaim
+	 * requested a movable allocation that does not heavily disrupt the
+	 * system then fail the allocation instead of entering direct reclaim.
 	 */
-	if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD))
+	if ((deferred_compaction || contended_compaction) &&
+						(gfp_mask & __GFP_NO_KSWAPD))
 		goto nopage;
 
 	/* Try direct reclaim and then allocating */
@@ -2505,6 +2512,7 @@ rebalance:
 					nodemask,
 					alloc_flags, preferred_zone,
 					migratetype, sync_migration,
+					&contended_compaction,
 					&deferred_compaction,
 					&did_some_progress);
 		if (page)
@@ -2569,8 +2577,6 @@ retry_cpuset:
 		page = __alloc_pages_slowpath(gfp_mask, order,
 				zonelist, high_zoneidx, nodemask,
 				preferred_zone, migratetype);
-	else
-		page->pfmemalloc = false;
 
 	trace_mm_page_alloc(page, order, gfp_mask, migratetype);
 
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 913d6bdfdda..ca05ba217f5 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -3016,7 +3016,8 @@ sub process {
 					$herectx .= raw_line($linenr, $n) . "\n";
 				}
 
-				if (($stmts =~ tr/;/;/) == 1) {
+				if (($stmts =~ tr/;/;/) == 1 &&
+				    $stmts !~ /^\s*(if|while|for|switch)\b/) {
 					WARN("SINGLE_STATEMENT_DO_WHILE_MACRO",
 					     "Single statement macros should not use a do {} while (0) loop\n" . "$herectx");
 				}