Merge branch 'master' into for-2.6.33

9 files changed, 124 insertions, 61 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index fd3386242cf..44cf6f0a3a6 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -128,12 +128,9 @@ config SPARSEMEM_VMEMMAP
 config MEMORY_HOTPLUG
 	bool "Allow for memory hot-add"
 	depends on SPARSEMEM || X86_64_ACPI_NUMA
-	depends on HOTPLUG && !(HIBERNATION && !S390) && ARCH_ENABLE_MEMORY_HOTPLUG
+	depends on HOTPLUG && ARCH_ENABLE_MEMORY_HOTPLUG
 	depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390)
 
-comment "Memory hotplug is currently incompatible with Software Suspend"
-	depends on SPARSEMEM && HOTPLUG && HIBERNATION && !S390
-
 config MEMORY_HOTPLUG_SPARSE
 	def_bool y
 	depends on SPARSEMEM && MEMORY_HOTPLUG
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 11aee09dd2a..67a33a5a1a9 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -604,10 +604,14 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 
 	/*
 	 * Finally, kill the kernel threads. We don't need to be RCU
-	 * safe anymore, since the bdi is gone from visibility.
+	 * safe anymore, since the bdi is gone from visibility. Force
+	 * unfreeze of the thread before calling kthread_stop(), otherwise
+	 * it would never exet if it is currently stuck in the refrigerator.
 	 */
-	list_for_each_entry(wb, &bdi->wb_list, list)
+	list_for_each_entry(wb, &bdi->wb_list, list) {
+		wb->task->flags &= ~PF_FROZEN;
 		kthread_stop(wb->task);
+	}
 }
 
 /*
diff --git a/mm/highmem.c b/mm/highmem.c
index 25878cc49da..9c1e627f282 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -426,16 +426,21 @@ void __init page_address_init(void)
 
 void debug_kmap_atomic(enum km_type type)
 {
-	static unsigned warn_count = 10;
+	static int warn_count = 10;
 
-	if (unlikely(warn_count == 0))
+	if (unlikely(warn_count < 0))
 		return;
 
 	if (unlikely(in_interrupt())) {
-		if (in_irq()) {
+		if (in_nmi()) {
+			if (type != KM_NMI && type != KM_NMI_PTE) {
+				WARN_ON(1);
+				warn_count--;
+			}
+		} else if (in_irq()) {
 			if (type != KM_IRQ0 && type != KM_IRQ1 &&
 			    type != KM_BIO_SRC_IRQ && type != KM_BIO_DST_IRQ &&
-			    type != KM_BOUNCE_READ) {
+			    type != KM_BOUNCE_READ && type != KM_IRQ_PTE) {
 				WARN_ON(1);
 				warn_count--;
 			}
@@ -452,7 +457,9 @@ void debug_kmap_atomic(enum km_type type)
 	}
 
 	if (type == KM_IRQ0 || type == KM_IRQ1 || type == KM_BOUNCE_READ ||
-			type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ) {
+			type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ ||
+			type == KM_IRQ_PTE || type == KM_NMI ||
+			type == KM_NMI_PTE ) {
 		if (!irqs_disabled()) {
 			WARN_ON(1);
 			warn_count--;
diff --git a/mm/ksm.c b/mm/ksm.c
index bef1af4f77e..5575f8628fe 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1012,6 +1012,7 @@ static struct rmap_item *unstable_tree_search_insert(struct page *page,
 		struct rmap_item *tree_rmap_item;
 		int ret;
 
+		cond_resched();
 		tree_rmap_item = rb_entry(*new, struct rmap_item, node);
 		page2[0] = get_mergeable_page(tree_rmap_item);
 		if (!page2[0])
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 821dee59637..2047465cd27 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -26,6 +26,7 @@
 #include <linux/migrate.h>
 #include <linux/page-isolation.h>
 #include <linux/pfn.h>
+#include <linux/suspend.h>
 
 #include <asm/tlbflush.h>
 
@@ -447,7 +448,8 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
 }
 #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
 
-static pg_data_t *hotadd_new_pgdat(int nid, u64 start)
+/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
+static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 {
 	struct pglist_data *pgdat;
 	unsigned long zones_size[MAX_NR_ZONES] = {0};
@@ -484,14 +486,18 @@ int __ref add_memory(int nid, u64 start, u64 size)
 	struct resource *res;
 	int ret;
 
+	lock_system_sleep();
+
 	res = register_memory_resource(start, size);
+	ret = -EEXIST;
 	if (!res)
-		return -EEXIST;
+		goto out;
 
 	if (!node_online(nid)) {
 		pgdat = hotadd_new_pgdat(nid, start);
+		ret = -ENOMEM;
 		if (!pgdat)
-			return -ENOMEM;
+			goto out;
 		new_pgdat = 1;
 	}
 
@@ -514,7 +520,8 @@ int __ref add_memory(int nid, u64 start, u64 size)
 		BUG_ON(ret);
 	}
 
-	return ret;
+	goto out;
+
 error:
 	/* rollback pgdat allocation and others */
 	if (new_pgdat)
@@ -522,6 +529,8 @@ error:
 	if (res)
 		release_memory_resource(res);
 
+out:
+	unlock_system_sleep();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(add_memory);
@@ -758,6 +767,8 @@ int offline_pages(unsigned long start_pfn,
 	if (!test_pages_in_a_zone(start_pfn, end_pfn))
 		return -EINVAL;
 
+	lock_system_sleep();
+
 	zone = page_zone(pfn_to_page(start_pfn));
 	node = zone_to_nid(zone);
 	nr_pages = end_pfn - start_pfn;
@@ -765,7 +776,7 @@ int offline_pages(unsigned long start_pfn,
 	/* set above range as isolated */
 	ret = start_isolate_page_range(start_pfn, end_pfn);
 	if (ret)
-		return ret;
+		goto out;
 
 	arg.start_pfn = start_pfn;
 	arg.nr_pages = nr_pages;
@@ -843,6 +854,7 @@ repeat:
 	writeback_set_ratelimit();
 
 	memory_notify(MEM_OFFLINE, &arg);
+	unlock_system_sleep();
 	return 0;
 
 failed_removal:
@@ -852,6 +864,8 @@ failed_removal:
 	/* pushback to free area */
 	undo_isolate_page_range(start_pfn, end_pfn);
 
+out:
+	unlock_system_sleep();
 	return ret;
 }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 1a4bf481378..7dbcb22316d 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -602,7 +602,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	struct page *newpage = get_new_page(page, private, &result);
 	int rcu_locked = 0;
 	int charge = 0;
-	struct mem_cgroup *mem;
+	struct mem_cgroup *mem = NULL;
 
 	if (!newpage)
 		return -ENOMEM;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index cdcedf66161..2bc2ac63f41 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1769,7 +1769,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 		 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
 		 */
 		alloc_flags &= ~ALLOC_CPUSET;
-	} else if (unlikely(rt_task(p)))
+	} else if (unlikely(rt_task(p)) && !in_interrupt())
 		alloc_flags |= ALLOC_HARDER;
 
 	if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) {
@@ -1817,9 +1817,9 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
 		goto nopage;
 
+restart:
 	wake_all_kswapd(order, zonelist, high_zoneidx);
 
-restart:
 	/*
 	 * OK, we're below the kswapd watermark and have kicked background
 	 * reclaim. Now things get more complex, so set up alloc_flags according
diff --git a/mm/percpu.c b/mm/percpu.c
index d90797160c2..5adfc268b40 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -355,62 +355,86 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
 }
 
 /**
- * pcpu_extend_area_map - extend area map for allocation
- * @chunk: target chunk
+ * pcpu_need_to_extend - determine whether chunk area map needs to be extended
+ * @chunk: chunk of interest
  *
- * Extend area map of @chunk so that it can accomodate an allocation.
- * A single allocation can split an area into three areas, so this
- * function makes sure that @chunk->map has at least two extra slots.
+ * Determine whether area map of @chunk needs to be extended to
+ * accomodate a new allocation.
  *
  * CONTEXT:
- * pcpu_alloc_mutex, pcpu_lock.  pcpu_lock is released and reacquired
- * if area map is extended.
+ * pcpu_lock.
  *
  * RETURNS:
- * 0 if noop, 1 if successfully extended, -errno on failure.
+ * New target map allocation length if extension is necessary, 0
+ * otherwise.
  */
-static int pcpu_extend_area_map(struct pcpu_chunk *chunk, unsigned long *flags)
+static int pcpu_need_to_extend(struct pcpu_chunk *chunk)
 {
 	int new_alloc;
-	int *new;
-	size_t size;
 
-	/* has enough? */
 	if (chunk->map_alloc >= chunk->map_used + 2)
 		return 0;
 
-	spin_unlock_irqrestore(&pcpu_lock, *flags);
-
 	new_alloc = PCPU_DFL_MAP_ALLOC;
 	while (new_alloc < chunk->map_used + 2)
 		new_alloc *= 2;
 
-	new = pcpu_mem_alloc(new_alloc * sizeof(new[0]));
-	if (!new) {
-		spin_lock_irqsave(&pcpu_lock, *flags);
+	return new_alloc;
+}
+
+/**
+ * pcpu_extend_area_map - extend area map of a chunk
+ * @chunk: chunk of interest
+ * @new_alloc: new target allocation length of the area map
+ *
+ * Extend area map of @chunk to have @new_alloc entries.
+ *
+ * CONTEXT:
+ * Does GFP_KERNEL allocation.  Grabs and releases pcpu_lock.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
+{
+	int *old = NULL, *new = NULL;
+	size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
+	unsigned long flags;
+
+	new = pcpu_mem_alloc(new_size);
+	if (!new)
 		return -ENOMEM;
-	}
 
-	/*
-	 * Acquire pcpu_lock and switch to new area map.  Only free
-	 * could have happened inbetween, so map_used couldn't have
-	 * grown.
-	 */
-	spin_lock_irqsave(&pcpu_lock, *flags);
-	BUG_ON(new_alloc < chunk->map_used + 2);
+	/* acquire pcpu_lock and switch to new area map */
+	spin_lock_irqsave(&pcpu_lock, flags);
+
+	if (new_alloc <= chunk->map_alloc)
+		goto out_unlock;
 
-	size = chunk->map_alloc * sizeof(chunk->map[0]);
-	memcpy(new, chunk->map, size);
+	old_size = chunk->map_alloc * sizeof(chunk->map[0]);
+	memcpy(new, chunk->map, old_size);
 
 	/*
 	 * map_alloc < PCPU_DFL_MAP_ALLOC indicates that the chunk is
 	 * one of the first chunks and still using static map.
 	 */
 	if (chunk->map_alloc >= PCPU_DFL_MAP_ALLOC)
-		pcpu_mem_free(chunk->map, size);
+		old = chunk->map;
 
 	chunk->map_alloc = new_alloc;
 	chunk->map = new;
+	new = NULL;
+
+out_unlock:
+	spin_unlock_irqrestore(&pcpu_lock, flags);
+
+	/*
+	 * pcpu_mem_free() might end up calling vfree() which uses
+	 * IRQ-unsafe lock and thus can't be called under pcpu_lock.
+	 */
+	pcpu_mem_free(old, old_size);
+	pcpu_mem_free(new, new_size);
+
 	return 0;
 }
 
@@ -1049,7 +1073,7 @@ static void *pcpu_alloc(size_t size, size_t align, bool reserved)
 	static int warn_limit = 10;
 	struct pcpu_chunk *chunk;
 	const char *err;
-	int slot, off;
+	int slot, off, new_alloc;
 	unsigned long flags;
 
 	if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
@@ -1064,14 +1088,25 @@ static void *pcpu_alloc(size_t size, size_t align, bool reserved)
 	/* serve reserved allocations from the reserved chunk if available */
 	if (reserved && pcpu_reserved_chunk) {
 		chunk = pcpu_reserved_chunk;
-		if (size > chunk->contig_hint ||
-		    pcpu_extend_area_map(chunk, &flags) < 0) {
-			err = "failed to extend area map of reserved chunk";
+
+		if (size > chunk->contig_hint) {
+			err = "alloc from reserved chunk failed";
 			goto fail_unlock;
 		}
+
+		while ((new_alloc = pcpu_need_to_extend(chunk))) {
+			spin_unlock_irqrestore(&pcpu_lock, flags);
+			if (pcpu_extend_area_map(chunk, new_alloc) < 0) {
+				err = "failed to extend area map of reserved chunk";
+				goto fail_unlock_mutex;
+			}
+			spin_lock_irqsave(&pcpu_lock, flags);
+		}
+
 		off = pcpu_alloc_area(chunk, size, align);
 		if (off >= 0)
 			goto area_found;
+
 		err = "alloc from reserved chunk failed";
 		goto fail_unlock;
 	}
@@ -1083,14 +1118,20 @@ restart:
 			if (size > chunk->contig_hint)
 				continue;
 
-			switch (pcpu_extend_area_map(chunk, &flags)) {
-			case 0:
-				break;
-			case 1:
-				goto restart;	/* pcpu_lock dropped, restart */
-			default:
-				err = "failed to extend area map";
-				goto fail_unlock;
+			new_alloc = pcpu_need_to_extend(chunk);
+			if (new_alloc) {
+				spin_unlock_irqrestore(&pcpu_lock, flags);
+				if (pcpu_extend_area_map(chunk,
+							 new_alloc) < 0) {
+					err = "failed to extend area map";
+					goto fail_unlock_mutex;
+				}
+				spin_lock_irqsave(&pcpu_lock, flags);
+				/*
+				 * pcpu_lock has been dropped, need to
+				 * restart cpu_slot list walking.
+				 */
+				goto restart;
 			}
 
 			off = pcpu_alloc_area(chunk, size, align);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index a1bc6b9af9a..9c590eef791 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1151,8 +1151,7 @@ static int try_to_unuse(unsigned int type)
 				} else
 					retval = unuse_mm(mm, entry, page);
 
-				if (set_start_mm &&
-				    swap_count(*swap_map) < swcount) {
+				if (set_start_mm && *swap_map < swcount) {
 					mmput(new_start_mm);
 					atomic_inc(&mm->mm_users);
 					new_start_mm = mm;